Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Everyone-Needs-A-Copilot/claude-copilot --skill megit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/me)<a href="https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/me"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/me.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.00566 |
| Opus 5 | $0.00019 | $0.00283 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
me scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineer
Use this skill to make focused, working code changes.
Operating Lens
- Read before editing.
- Follow existing code style, helpers, and module boundaries.
- Fix root causes instead of symptoms.
- Add tests in proportion to risk and blast radius.
- Keep unrelated refactors out of the change.
- Use Live Docs before coding against installed third-party package APIs.
- Treat
$qaas required for implementation work that needs verification.
Success Criteria
- Code compiles or the relevant build check passes.
- Focused tests or checks run for the changed behavior.
- New or changed behavior has proportional test coverage.
- Edge cases and errors are handled.
- Implementation details are stored as a
tcwork product when task context exists. - QA-required tasks carry
metadata.requiresQa=trueand are routed to$qa.
Workflow
- Confirm the task, plan, or bug is framed clearly enough to implement.
- Check task context with
tc task get <taskId> --jsonwhen available. - Hydrate config and search memory when
ccis configured. - Inspect the relevant files, current tests, and local patterns.
- Run
cc docs get <pkg> --topic <area> --jsonbefore using third-party APIs. - Make the smallest coherent change.
- Run focused validation first, then broader checks when warranted.
- Store implementation details as a
codework product. - Route to
$qa; do not treat implementation as the final gate.
Iteration Loop
Make a focused change, validate observable behavior, analyze failures, and refine. Stop only when validation passes, the task is genuinely blocked, or the remaining risk is explicitly reported.
Methodology
Kent Beck's simple design priority: passes tests, reveals intention, removes duplication, then minimizes elements.
Anti-Generic Rules
- Do not introduce an abstraction before duplication or complexity earns it.
- Do not refactor unrelated code in the same change.
- Do not leave implementation work unverified when tests or checks are relevant.
- Do not rely on remembered third-party APIs when Live Docs or local package files can verify them.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 70 lines · 39 tokens per session scan A b238a75165be
me is a skill published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 566 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
ward
Ward the codebase — an ad-hoc test-gap audit that reveals unguarded code (untested functions, uncovered edge cases, missing error-handling and integration tests) and conjures ready-to-paste test skeletons as protective wards against regression, surfaced inline in the session. Scoped to your current diff by default, or…
ralphctl-debugging-and-error-recovery
Systematic root-cause debugging. Use when tests fail, builds break, or behaviour does not match expectations. Follow stop-the-line → reproduce → localize → reduce → root-cause → guard-with-regression-test → verify, not guessing; the reproduction and regression steps follow the same red-green discipline as…
health-check
Run a comprehensive codebase health check — tests, linting, coverage, complexity, and dependency audit. Compare with previous runs to detect regressions.
bug-fix
A structured bug-fixing workflow that takes a problem from reproduction and evidence-based cause finding through approval, implementation, testing, and cleanup.
qa-cycle
QA + bugfix cycle until it passes.
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.