Not in the top 1,000 by GitHub stars
Neeeophytee/ai-cost-cutter-skills
10 skills that cut your AI bill with proof instead of vibes. MIT, works in Claude Code, Codex, Cursor. Every skill's check is executed by CI.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/advisor-call-budget/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/cheap-swap-guard/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/context-diet/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/free-model-triage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/free-tier-batch-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/model-bakeoff/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/reasoning-effort-throttle/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/route-cheap-escalate-hard/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/tested-fallback/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
skills/token-receipts-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6899513cfbf6 → 6899513cfbf6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6899513cfbf6
No earlier version was observed for comparison.
Verified commit 6899513cfbf628000d639a465e1b7d3b249e9fb4
git clone --filter=blob:none --no-checkout https://github.com/Neeeophytee/ai-cost-cutter-skills.git .hotskills/neeeophytee-ai-cost-cutter-skills && git -C .hotskills/neeeophytee-ai-cost-cutter-skills checkout --detach 6899513cfbf628000d639a465e1b7d3b249e9fb4
# Copy each selected skill directory from .hotskills/neeeophytee-ai-cost-cutter-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/Neeeophytee/ai-cost-cutter-skills.git .hotskills/neeeophytee-ai-cost-cutter-skills && git -C .hotskills/neeeophytee-ai-cost-cutter-skills checkout --detach 6899513cfbf628000d639a465e1b7d3b249e9fb4
# Copy each selected skill directory from .hotskills/neeeophytee-ai-cost-cutter-skills into .agents/skills/<skill-name>/Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- advisor-call-budget
skills/advisor-call-budget - cheap-swap-guard
skills/cheap-swap-guard - context-diet
skills/context-diet - free-model-triage
skills/free-model-triage - free-tier-batch-plan
skills/free-tier-batch-plan - model-bakeoff
skills/model-bakeoff - reasoning-effort-throttle
skills/reasoning-effort-throttle - route-cheap-escalate-hard
skills/route-cheap-escalate-hard - tested-fallback
skills/tested-fallback - token-receipts-audit
skills/token-receipts-audit
How it works
advisor-call-budget
When your agent uses it
Enforce a hard cap and a drift-check when a cheap executor model consults an expensive advisor model, and compute the effective cost from actual call counts instead of a benchmark's assumed rate. Use when the user adopts the advisor or orchestrator pattern, pairs a cheap model with an expensive reviewer, or quotes a benchmark discount like "63% of the price".
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,094 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
../../.claude-plugin/marketplace.jsonasset440 bytes../../.claude-plugin/plugin.jsonasset561 bytesSKILL.mdcore4,498 bytesSKILL.mdcore4,498 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcheap-swap-guard
When your agent uses it
Before swapping any workload to a cheaper model, declare the cases the premium model still dominates and prove they keep routing to premium. Use when the user wants to "just switch" to a cheaper model (text, image, or video), or asks whether a cheap model is good enough to replace an expensive one.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
987 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore4,011 bytesSKILL.mdcore4,011 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcontext-diet
When your agent uses it
Cut agent token spend by shrinking what enters the context window. Index the repo or corpus once and query it instead of re-reading files on every question. Use when the user complains their coding agent burns tokens, the context fills up fast, the same files get read repeatedly, or the bill scales with conversation length.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
849 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore3,571 bytesSKILL.mdcore3,571 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfree-model-triage
When your agent uses it
Route high-volume, low-stakes triage (reading piles, inbox summaries, needs-reply flags) to a free model with a strict output schema. Use when the user wants one-line summaries of many items cheaply, asks to triage email, articles, or reports with AI, or wants to decide what's worth reading without paying premium rates for it.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
931 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore3,813 bytesSKILL.mdcore3,813 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfree-tier-batch-plan
When your agent uses it
Size a big one-time batch job against a free tier's rate limit and token budget BEFORE starting it, with a proven wall-clock ETA. Use when the user wants to label a dataset, summarize an archive, or process a large backlog for free (or on a tiny rate limit), or asks "will this finish overnight?"
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
875 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore3,362 bytesSKILL.mdcore3,362 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmodel-bakeoff
When your agent uses it
Choose a model with evidence by running the few prompts that actually matter across candidate models inside a free tier's caps, picking by a stated criterion. Use when the user asks "which model should I use", wants to evaluate a newly launched model, or is choosing between models for a specific task.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
934 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore3,720 bytesSKILL.mdcore3,720 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubreasoning-effort-throttle
When your agent uses it
Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task. Use when the user runs a reasoning model in an agent and the bill is dominated by output or thinking tokens, or asks about reasoning_effort, thinking budgets, or why a cheap model is still expensive to run.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
877 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore3,749 bytesSKILL.mdcore3,749 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubroute-cheap-escalate-hard
When your agent uses it
Cut LLM spend by routing bulk work to a cheap model and escalating only the hard turns to a premium one. Use when the user says their AI bill is too high, asks to "use a cheaper model", or wants two-tier model routing without losing quality on the hard tasks.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
998 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore4,013 bytesSKILL.mdcore4,013 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtested-fallback
When your agent uses it
Pin an open-weights fallback model with a tested-on date and real smoke prompts, so a pulled or deprecated model is a two-minute config swap instead of a lost week. Use when the user worries a model could vanish or be deprecated, builds anything important on one model, or asks about model failover and resilience.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,000 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore4,117 bytesSKILL.mdcore4,117 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtoken-receipts-audit
When your agent uses it
Attribute AI usage by tokens AND dollars so a high-volume cheap model is never mistaken for the expensive one. Use when the user asks where their AI spend actually goes, why the bill is high, which model is costing the most, or wants a usage audit across agents and models.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
1,043 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Prove it
- Guardrails
Files
SKILL.mdcore3,847 bytesSKILL.mdcore3,847 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- advisor-call-budget
- cheap-swap-guard
- context-diet
- free-model-triage
- free-tier-batch-plan
- model-bakeoff
- reasoning-effort-throttle
- route-cheap-escalate-hard
- tested-fallback
- token-receipts-audit
Repository facts
- License
- No license detected
- Created
- Jul 13, 2026
- Last pushed
- Jul 13, 2026
- Forks
- 2
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 10 notes
skills/advisor-call-budget/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/cheap-swap-guard/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/context-diet/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/free-model-triage/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/free-tier-batch-plan/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/model-bakeoff/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/reasoning-effort-throttle/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/route-cheap-escalate-hard/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/tested-fallback/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/token-receipts-audit/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 24 network referencesin 11 files: free-model-triage/SKILL.md:12 route-cheap-escalate-hard/SKILL.md:21 tested-fallback/SKILL.md:25 and 8 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 24 signals by file
.claude-plugin/plugin.json
- Network accessline 4
"version": "1.0.0", "author": { "name": "Neeeophytee" }, "homepage": "https://github.com/Neeeophytee/ai-cost-cutter-skills" - Network accessline 5
"author": { "name": "Neeeophytee" }, "homepage": "https://github.com/Neeeophytee/ai-cost-cutter-skills" } - Network accessline 6
"homepage": "https://github.com/Neeeophytee/ai-cost-cutter-skills"
skills/advisor-call-budget/SKILL.md
- Network accessline 53
<sub>Backed by a machine-verified recipe, re-checked by CI: [Advisor pattern: cap how often the expensive model gets called](https://flowstacks.xyz/workflows/advisor-pattern-call-budget-and-drift-check)</sub>
skills/cheap-swap-guard/SKILL.md
- Network accessline 55
<sub>Backed by a machine-verified recipe, re-checked by CI: [Swap to a cheap image model, but guard the cases it loses](https://flowstacks.xyz/workflows/image-gen-cheap-swap-with-text-guard)</sub>
skills/context-diet/SKILL.md
- Network accessline 52
<sub>Backed by a machine-verified recipe, re-checked by CI: [Wire the knowledge graph, stop re-reading files](https://flowstacks.xyz/workflows/codebase-memory-mcp-token-savings)</sub>
skills/free-model-triage/SKILL.md
- Network accessline 12
1. Confirm the pile fits the caps: daily item count vs. 50/day (or 1,000/day post-credit). Over the cap means batching across days or the cheapest paid model; still pennies. 2. Point any OpenAI-compatible client at `https://openrouter.ai/ap - Network accessline 13
2. Point any OpenAI-compatible client at `https://openrouter.ai/api/v1` with a model whose id ends in `:free`. That suffix is the contract; without it the "free" triage quietly bills. - Network accessline 21
cat > triage.json <<'JSON' { "base_url": "https://openrouter.ai/api/v1", - Network accessline 22
{ "base_url": "https://openrouter.ai/api/v1", "model": "deepseek/deepseek-r1:free", - Network accessline 23
"base_url": "https://openrouter.ai/api/v1", - Network accessline 56
<sub>Backed by a machine-verified recipe, re-checked by CI: [Let a free model triage your reading](https://flowstacks.xyz/workflows/openrouter-free-triage)</sub>
skills/free-tier-batch-plan/SKILL.md
- Network accessline 53
<sub>Backed by a machine-verified recipe, re-checked by CI: [Grind a huge one-time job overnight on a free tier](https://flowstacks.xyz/workflows/free-tier-overnight-batch)</sub>
skills/model-bakeoff/SKILL.md
- Network accessline 50
<sub>Backed by a machine-verified recipe, re-checked by CI: [A GitHub Models bake-off that fits the free cap](https://flowstacks.xyz/workflows/github-models-prompt-bakeoff)</sub>
skills/reasoning-effort-throttle/SKILL.md
- Network accessline 47
<sub>Backed by a machine-verified recipe, re-checked by CI: [A one-line reasoning-effort throttle](https://flowstacks.xyz/workflows/hermes-deepseek-v4-flash-effort-throttle)</sub>
skills/route-cheap-escalate-hard/SKILL.md
- Network accessline 21
cat > routing.json <<'JSON' { "base_url": "https://openrouter.ai/api/v1", - Network accessline 22
{ "base_url": "https://openrouter.ai/api/v1", "default_model": "z-ai/glm-5.2", - Network accessline 23
"base_url": "https://openrouter.ai/api/v1", - Network accessline 50
<sub>Backed by a machine-verified recipe, re-checked by CI: [Run GLM-5.2 for the bulk, escalate the hard turns to Opus 4.8](https://flowstacks.xyz/workflows/glm-52-route-bulk-escalate-opus)</sub>
skills/tested-fallback/SKILL.md
- Network accessline 25
cat > failover.json <<'JSON' { "base_url": "https://openrouter.ai/api/v1", - Network accessline 26
{ "base_url": "https://openrouter.ai/api/v1", "primary": "anthropic/claude-fable-5", - Network accessline 27
"base_url": "https://openrouter.ai/api/v1", - Network accessline 60
<sub>Backed by a machine-verified recipe, re-checked by CI: [Route through a gateway with a tested open-weights fallback](https://flowstacks.xyz/workflows/model-failover-tested-open-fallback)</sub>
skills/token-receipts-audit/SKILL.md
- Network accessline 56
<sub>Backed by a machine-verified recipe, re-checked by CI: [Read your token receipts right](https://flowstacks.xyz/workflows/token-volume-vs-cost-receipts)</sub>
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 21 facts
- Network access in prose of the SKILL.mdadvisor-call-budget/SKILL.md:53Low confidence
- Network access in prose of the SKILL.mdcheap-swap-guard/SKILL.md:55Low confidence
- Network access in prose of the SKILL.mdcontext-diet/SKILL.md:52Low confidence
- Network access in prose of the SKILL.mdfree-model-triage/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdfree-model-triage/SKILL.md:13Low confidence
- Network access in code of the SKILL.mdfree-model-triage/SKILL.md:21High confidence
- Network access in code of the SKILL.mdfree-model-triage/SKILL.md:22High confidence
- Network access in code of the SKILL.mdfree-model-triage/SKILL.md:23High confidence
- Network access in prose of the SKILL.mdfree-model-triage/SKILL.md:56Low confidence
- Network access in prose of the SKILL.mdfree-tier-batch-plan/SKILL.md:53Low confidence
- Network access in prose of the SKILL.mdmodel-bakeoff/SKILL.md:50Low confidence
- Network access in prose of the SKILL.mdreasoning-effort-throttle/SKILL.md:47Low confidence
- Network access in code of the SKILL.mdroute-cheap-escalate-hard/SKILL.md:21High confidence
- Network access in code of the SKILL.mdroute-cheap-escalate-hard/SKILL.md:22High confidence
- Network access in code of the SKILL.mdroute-cheap-escalate-hard/SKILL.md:23High confidence
- Network access in prose of the SKILL.mdroute-cheap-escalate-hard/SKILL.md:50Low confidence
- Network access in code of the SKILL.mdtested-fallback/SKILL.md:25High confidence
- Network access in code of the SKILL.mdtested-fallback/SKILL.md:26High confidence
- Network access in code of the SKILL.mdtested-fallback/SKILL.md:27High confidence
- Network access in prose of the SKILL.mdtested-fallback/SKILL.md:60Low confidence
- Network access in prose of the SKILL.mdtoken-receipts-audit/SKILL.md:56Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/advisor-call-budget/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/advisor-call-budget/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/advisor-call-budget/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/advisor-call-budget/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
