Menu

Not in the top 1,000 by GitHub stars

alexandre180345678910-cmd/tracker-skills

Evidence-first agent skills for Claude Code and Codex: plan, build, review and ship like a careful senior engineer.

Engineering

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/claude-codex-pair/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → b0f612844e1a

No earlier version was observed for comparison.

Compare on GitHub

skills/code-health-audit/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → b0f612844e1a

No earlier version was observed for comparison.

Compare on GitHub

skills/ship-with-confidence/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → b0f612844e1a

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit b0f612844e1aa7d1f2817454d1a5fb60457b8a52

3GitHub stars
Not availablestars in 7 days
3skills in this repository
1commit in 30 days

Heat

Insufficient history

Not enough history yet to measure heat. It appears after a few days of data.

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Nov 2, 2026Nov 2, 20263

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

claude-codex-pair

When your agent uses it

Coordinate Claude Code and Codex on the same software task with one active writer, an independent read-only reviewer, explicit ownership transfers, evidence-based handoffs, and safe use of the official Codex plugin for Claude Code. Use when the user asks Claude and Codex to work together, delegate to each other, review or challenge each other's work, transfer a session, rescue a task, or continue work across both agents. Do not use for ordinary single-agent implementation or factual questions.

What it loads into context

Frontmatter

130 tokens

Always available to the agent

SKILL.md

1,923 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Non-Negotiable Invariant
  2. Select the Smallest Collaboration Mode
  3. Claude Code → Codex Bridge
  4. Compatibility with TLC Spec-Driven
  5. Shared Sources of Truth
  6. Handoff Contract
  7. Review Loop
  8. Completion Gate

Files

  • SKILL.mdcore9,111 bytes
Read SKILL.md

# Claude–Codex Pair

Treat Claude Code and Codex as a writer–challenger pair. The roles rotate by task; neither
agent is permanently the lead. Optimize for independent evidence, not agreement.

## Non-Negotiable Invariant

Exactly one agent owns write access to the current worktree at a time.

- The **writer** may inspect, edit, test, and create local commits within the accepted scope.
- The **challenger** is read-only. It attempts to falsify the writer's result with code,
  tests, specs, logs, documentation, and reproducible commands.
- A review verdict never grants permission to edit.
- Do not run two write-capable agents concurrently in the same worktree.
View the complete source on GitHub

Skills included

  • claude-codex-pair
  • code-health-audit
  • ship-with-confidence

Repository facts

License
MIT
Created
Nov 1, 2026
Last pushed
Nov 1, 2026
Forks
0
Open issues
0
Project activity
Active

Before you install

Local scripts

Automated 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 1 note
  • skills/code-health-audit/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 45 signals by file

skills/ship-with-confidence/references/sources.md

  • Network accessline 5
    | Source | Audited commit | License | Concepts used | | --- | --- | --- | --- | | [mattpocock/skills](https://github.com/mattpocock/skills) | `068b6e0c62393147daf03530149cdce209c93da8` | MIT | deep modules, diagnosis, TDD, specification and
  • Network accessline 6
    | --- | --- | --- | --- | | [mattpocock/skills](https://github.com/mattpocock/skills) | `068b6e0c62393147daf03530149cdce209c93da8` | MIT | deep modules, diagnosis, TDD, specification and review workflow | | [obra/superpowers](https://github
  • Network accessline 7
    | [mattpocock/skills](https://github.com/mattpocock/skills) | `068b6e0c62393147daf03530149cdce209c93da8` | MIT | deep modules, diagnosis, TDD, specification and review workflow |
  • Network accessline 8
    | [obra/superpowers](https://github.com/obra/superpowers) | `b36e0829c6d0140e93cfef2ca599b1b07d4a7797` | MIT | isolated workspaces, evidence-first execution, systematic debugging |
  • Network accessline 9
    | [wshobson/agents](https://github.com/wshobson/agents) | `d6837ae274c2cd817acad3fb98f193a4390a4c3e` | MIT | specialist routing and delivery coverage |
  • Network accessline 10
    | [nextlevelbuilder/ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) | `a38d04c3d5c298c851dbe5e6ee1965ee3de42cb5` | MIT | UI/UX pattern catalog and stack recommendations |
  • Network accessline 11
    | [semgrep/skills](https://github.com/semgrep/skills) | `68177b8830f96cd9d10dacbb14dde2566360503d` | Semgrep Rules License 1.0 | concrete code-security categories and proactive security review |
  • Network accessline 12
    | [OWASP/secure-agent-playbook](https://github.com/OWASP/secure-agent-playbook) | `79fea6b9115b55687818f8c4073844ee9ba907a6` | CC BY 4.0 | ASVS/API-oriented coverage, structured findings, agent threat modeling |
  • Network accessline 13
    | [trailofbits/skills](https://github.com/trailofbits/skills) | `4db88ee79db0a68bbe049fe827e272ee2bc19510` | CC BY-SA 4.0 | trust-boundary context and evidence-led audit practices |
  • Network accessline 14
    | [grafana/k6](https://github.com/grafana/k6) | reviewed 2026-08-15 | AGPL-3.0 | executable performance thresholds and load-test regression gates |
  • Network accessline 15
    | [infracost/infracost](https://github.com/infracost/infracost) | reviewed 2026-08-15 | Apache-2.0 | shift-left infrastructure cost diffs and FinOps policy gates |
  • Network accessline 16
    | [opencost/opencost](https://github.com/opencost/opencost) | reviewed 2026-08-15 | Apache-2.0 | vendor-neutral workload cost allocation and unit attribution |
  • Network accessline 17
    | [OpenTelemetry specifications](https://github.com/open-telemetry/opentelemetry-specification) | reviewed 2026-08-15 | Apache-2.0 | request traces, metrics, bounded cardinality, and aggregation |
  • Network accessline 18
    | [FinOps Foundation unit economics](https://www.finops.org/framework/capabilities/unit-economics/) | reviewed 2026-08-15 | CC BY 4.0 | cost per request/outcome and business-value normalization |
  • Network accessline 19
    | [OpenAI model optimization guide](https://developers.openai.com/api/docs/guides/latest-model) | reviewed 2026-08-15 | documentation terms | lean prompts, context discipline, caching, reasoning reuse, and measured model/effort selection |
  • Network accessline 20
    | [Anthropic prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) | reviewed 2026-08-15 | documentation terms | stable-prefix caching, cache lifetime/cost, and tool-schema context |
  • Network accessline 21
    | [SkillReducer](https://arxiv.org/abs/2603.29919) | v1 reviewed 2026-08-15 | paper terms | concise actionable skills and reduced context |
  • Network accessline 22
    | [Skill_EE](https://github.com/1Reminding/Skill_EE) | reviewed 2026-08-15 | no license established; concepts only | cost-aware skill rewriting evaluated across models; no code/content incorporated |
  • Network accessline 23
    | [Pact](https://github.com/pact-foundation/pact-js) | reviewed 2026-08-15 | MIT | consumer-driven contract verification |
  • Network accessline 24
    | [OpenSSF Scorecard](https://github.com/ossf/scorecard) | reviewed 2026-08-15 | Apache-2.0 | supply-chain posture signals |
  • Network accessline 25
    | [SLSA build provenance](https://github.com/slsa-framework/slsa/blob/main/spec/build-provenance.md) | reviewed 2026-08-15 | Community Specification License 1.0 for adopted specification content; Apache-2.0 for pre-adoption content/code | a
  • Network accessline 26
    | [Google OSS-Fuzz](https://github.com/google/oss-fuzz) | reviewed 2026-08-15 | Apache-2.0 | continuous fuzzing and adversarial verification patterns |
  • Network accessline 27
    | [Google SRE recovery lessons](https://sre.google/static/pdf/LessonsLearnedFromTwoDecades.pdf) | reviewed 2026-08-15 | publication terms | restore testing, recovery evidence, and operational resilience |

skills/ship-with-confidence/scripts/audit_context.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/evaluate_skill.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/final-gate.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/ship-with-confidence/scripts/final-push.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/ship-with-confidence/scripts/git-checkpoint.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/ship-with-confidence/scripts/project_profile.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/secret_guard.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/test_evaluate_skill.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/test_project_profile.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/test_secret_guard.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 22
    [Credential-related source omitted]
  • Access to secretsline 36
    [Credential-related source omitted]
  • Access to secretsline 38
    [Credential-related source omitted]
  • Access to secretsline 39
    [Credential-related source omitted]
  • Access to secretsline 47
    [Credential-related source omitted]
  • Access to secretsline 48
    [Credential-related source omitted]
  • Access to secretsline 57
    [Credential-related source omitted]
  • Access to secretsline 58
    [Credential-related source omitted]

skills/ship-with-confidence/scripts/test_validate_evidence.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/validate-install.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/ship-with-confidence/scripts/validate_evidence.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/ship-with-confidence/scripts/validate_skill.py

  • Executable scriptline 1
    #!/usr/bin/env python3

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: 45 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/claude-codex-pair/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/claude-codex-pair/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/claude-codex-pair/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/claude-codex-pair/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/claude-codex-pair/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/claude-codex-pair/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.

You might also use

KKKKhazix/khazix-skills

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

22kGitHub stars

NVIDIA/skills

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

3.9kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

186kGitHub stars

foryourhealth111-pixel/Vibe-Skills

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

3.8kGitHub stars

Nanako0129/sepia

De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture…

3.7kGitHub stars

FrancyJGLisboa/agent-skills-platform

Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

2.4kGitHub stars