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 agentmods add skills/apurvbazari/claude-plugins/feature-donenpx skills add ApurvBazari/claude-plugins --skill feature-donegit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWrote 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/apurvbazari/claude-plugins/feature-done)<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/feature-done"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/feature-done.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 | $0.00018 | $0.00479 |
| Opus 5 | $0.00009 | $0.00239 |
| Sonnet 5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
feature-done 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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature-done — Feature Completion Checklist
Run this before considering a plugin feature complete. Validates the plugin, checks documentation, and suggests a commit.
Step 1: Run Validation
Invoke the /validate skill to run all quality checks. If any check returns FAIL, stop and report the failures — they must be fixed before proceeding.
If only WARNs are present, note them and continue.
Step 2: Check Documentation
Review the git diff to identify what changed. For each modified plugin:
- README.md: If user-facing behavior changed (new skill, new command, changed arguments), verify README is updated
- Plugin CLAUDE.md: If internal conventions changed (new patterns, new architecture), verify the subdirectory CLAUDE.md is updated
- CHANGELOG.md: Verify there's an entry for this change
Report any missing documentation updates as items to address.
Step 3: Version Check
If plugin code changed (not just docs):
- Check if
plugin.jsonversion was bumped - Check if
marketplace.jsonversion was updated to match - If not bumped, suggest a version bump (patch for fixes, minor for features)
Step 4: Git Status Review
Run git status and review:
- Are there untracked files that should be committed?
- Are there files that should NOT be committed (temporary files, local configs)?
- Is the working tree clean enough for a commit?
Step 5: Suggest Commit
Based on the changes, suggest a conventional commit message:
type(scope): description
- type: feat, fix, refactor, docs, chore
- scope: plugin name (onboard, notify, handoff) or repo-level
- description: concise "why" in imperative mood
Present the suggested message and ask if the user wants to commit.
Key Rules
- Always run /validate first — it's the foundation
- Don't auto-commit — suggest and let the user decide
- Version bumps are mandatory for code changes, optional for doc-only changes
- One logical change per commit — if multiple plugins changed independently, suggest separate commits
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.
- 4d ago First seen · 60 lines · 18 tokens per session scan A 18bdec899289
feature-done is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 29d ago), licensed MIT. It adds 18 tokens to every session and 479 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
novu-prepare-pr
Post-implementation PR prep for Novu feature branches — quality passes, commit/PR hygiene, CI triage, and review feedback. Use after feature work is done, when the user asks to prepare a PR, ship a branch, fix CI, address review comments, or babysit a pull request before merge.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
aidd-vcs:01:commit
Create an atomic git commit with conventional message format. Supports interactive mode (human-driven, may split commits, asks approval) and auto mode (agent-driven, no approval, single commit). Use when the user says "commit", "git commit", "create a commit", "commit my changes", "commit and push", or invokes…
commit
Create a well-formatted git commit.
lesson-close
Закрыть текущее занятие. Финализирует lesson/YYYY-MM-DD.md (frontmatter status, метаданные времени, длительность), делает commit + push в репо DS-personal-guide. Триггерит замкнутый контур доставки — после push → GitHub webhook → bot oauthserver.py:/webhook/github/workbook → synconeusertodt → ЦД обновляется в Neon.…