Borrowing it
Nothing to install: this file belongs to bayesimpact/bayes-platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bayesimpact/bayes-platform/main/.claude/skills/end-feature/SKILL.mdgit clone --depth 1 https://github.com/bayesimpact/bayes-platformWrote 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/bayesimpact/bayes-platform/end-feature)<a href="https://agentmods.dev/skills/bayesimpact/bayes-platform/end-feature"><img src="https://agentmods.dev/badge/skills/bayesimpact/bayes-platform/end-feature/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bayesimpact/bayes-platform/end-feature"><img src="https://agentmods.dev/badge/skills/bayesimpact/bayes-platform/end-feature.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.01114 |
| Opus 5 | $0.00026 | $0.00557 |
| Sonnet 5 | $0.00011 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
end-feature 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 2d ago.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap up a feature by running its final steps. Present a checklist form, then execute only the checked steps, in the fixed order below.
Step 0 — Show the checklist form
Before doing anything, call AskUserQuestion with a single multi-select question so the user can check/uncheck the steps (list them as the options; the user unchecks any they want to skip):
- Update changelog — add an entry under
## [Unreleased]inCHANGELOG.md - Create a branch — move current work onto a feature branch
- Run tests-parallel —
make tests-parallel - Create a PR — open a pull request with
gh
All steps are pre-selected by default EXCEPT the changelog, which is optional: pre-select it only when the change is visible to end users or security-relevant. Leave it unchecked for internal work — refactors, CI/tooling, docs, tests. Mention in the question why you left it unchecked; the user can still check it.
Use header: "Steps", multiSelect: true. Whatever the user leaves checked is the set to run.
Then run the checked steps strictly in this order (skip unchecked ones):
1. Update changelog
Only if checked. Edit CHANGELOG.md, adding a line under ## [Unreleased]:
- New capability →
### Added; modified behavior →### Changed; bug fix →### Fixed; security hardening or vulnerability fix →### Security. - Write for end users, not developers — describe the visible outcome, not entities/services/migrations.
- Prefix with
(beta)if the feature is behind a flag or not yet exposed in the UI. - Write in STE (Simplified Technical English): short sentences (max 20 words), one fact per sentence, active voice.
- One sentence per entry. Even a large feature gets one headline sentence naming the capability or the new status (e.g. "Agents now have a draft and a published version of their settings."), not the mechanics. No sub-bullets. Never chain clauses with ";", "—", or "so".
- Name the capability, not the UI: no button placement, labels, colors, or click behavior. Keep dates and required user actions.
- Merge entries that belong to the same change into one. Delete an entry whose information is already carried by another.
- Verify before writing: check the actual commits/code for how a change works (runtime vs data migration, full vs partial scope). Scope claims exactly — write "New CSV extraction runs are personal." when existing data is unaffected.
- Do not add an entry for a bug that was never in a released version. Check that the bug's cause was in the last release tag before listing a fix.
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.
- 2d ago First seen · 78 lines · 53 tokens per session scan A 444a882ca0d1
end-feature is a skill published in the GitHub repository bayesimpact/bayes-platform (18 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,114 once invoked, about $0.0003 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 2026-09-14.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.