Not in the top 1,000 by GitHub stars
alperiox/prime-worker
Claude Code skill for delegating stateful, multi-turn work to a local prime-agent subagent
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/prime-worker/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 94c050d24dda
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 94c050d24ddadf6274ee68f51b607f34226928b3
git clone --filter=blob:none --no-checkout https://github.com/alperiox/prime-worker.git .hotskills/alperiox-prime-worker && git -C .hotskills/alperiox-prime-worker checkout --detach 94c050d24ddadf6274ee68f51b607f34226928b3
# Copy each selected skill directory from .hotskills/alperiox-prime-worker into .claude/skills/<skill-name>/0GitHub stars
0stars in 7 days
1skill in this repository
5commits in 30 days
Heat
1.4- 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
- prime-worker
skills/prime-worker
How it works
prime-worker
When your agent uses it
Use when delegating multi-turn work to a cheap local prime-agent subagent that must remember context across turns — iterating on a refactor, working through a subsystem, branching a what-if from an established investigation. Triggers when a delegated task needs more than one exchange, or when an earlier delegation should be continued rather than restarted. For one-shot descriptive reading that needs no follow-up, use delegate-bulk-read instead.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
3,595 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
- Overview
- Choosing the Model: Ask First
- The Verbs
- Autonomous Mode
- Refinement: Letting the Worker Learn
- Scoping
- Verification
- Failure Modes
- Red Flags
Scripts executed separately
scripts/pw
Files
../../.claude-plugin/marketplace.jsonasset460 bytes../../.claude-plugin/plugin.jsonasset494 bytesSKILL.mdcore15,275 bytesSKILL.mdcore15,275 bytesSKILL.mdcore15,275 bytesSKILL.mdcore15,275 bytesSKILL.mdcore15,275 bytesSKILL.mdcore15,275 bytesscripts/pwruns13,600 bytes
Read SKILL.md
# Prime Worker
## Overview
`prime-agent` is installed locally and runs models from the user's **OpenCode Go subscription**. Because that is a subscription, per-token price is *not* the thing to optimize — the real axes are context window, latency, and how much the model can be trusted with the task.
**A worker is a named directory.** `~/.claude/prime-workers/<name>/` holds exactly one session `.jsonl` plus a `worker.env` recording the `--cwd` and `--model` it was spawned with. The name is the only handle you ever need.
Drive it with the `pw` script bundled beside this skill: `scripts/pw`, relative to this file's own directory, or plain `pw` when it is on `PATH`. Do not hand-roll `prime-agent` invocations — the raw CLI has a trap that silently breaks continuity (see Failure Modes).
## Choosing the Model: Ask First
**Ask the user which model to use before spawning a worker.** Default to `deepseek-v4-flash`, but present the choice — the user tracks which models are performing well and that changes faster than this file does.
Skills included
- prime-worker
Repository facts
- License
- MIT
- Created
- Sep 25, 2026
- Last pushed
- Oct 12, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 5 notes
skills/prime-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/prime-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/prime-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/prime-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/prime-worker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 3 dangerous shell commandsin 1 file: prime-worker/scripts/pw:104
- 4 network referencesin 1 file: .claude-plugin/plugin.json:7
- No hidden or obfuscated text
- No instruction overrides
- 1 executable scriptin 1 file: prime-worker/scripts/pw:1
- No access to secrets
- No requests to vote in Hot
Show all 8 signals by file
.claude-plugin/plugin.json
- Network accessline 7
"email": "itsc0508@gmail.com" }, "homepage": "https://github.com/alperiox/prime-worker", - Network accessline 8
}, "homepage": "https://github.com/alperiox/prime-worker", "repository": "https://github.com/alperiox/prime-worker", - Network accessline 9
"homepage": "https://github.com/alperiox/prime-worker", - Network accessline 10
"repository": "https://github.com/alperiox/prime-worker",
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: 4 facts
- Executable script in code of a file that runsprime-worker/scripts/pw:1High confidence
- Dangerous shell operation in code of a file that runsprime-worker/scripts/pw:104High confidence
- Dangerous shell operation in code of a file that runsprime-worker/scripts/pw:105High confidence
- Dangerous shell operation in code of a file that runsprime-worker/scripts/pw:303High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/prime-worker/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/prime-worker/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/prime-worker/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/prime-worker/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/prime-worker/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.
