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/kirodotdev/kirocrew/feature-requestnpx skills add kirodotdev/KiroCrew --skill feature-requestgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWhat 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 | $0.00043 | $0.01897 |
| Opus 5 | $0.00022 | $0.00949 |
| Sonnet 5 | $0.00009 | $0.00379 |
| Haiku 4.5 | $0.00004 | $0.00190 |
Grade A, and why
feature-request 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Request / Issue Report
Conversational workflow for gathering user feedback and creating GitHub Issues on the KiroCrew repository.
Trigger: User clicks "Request a Feature" button, or says "report a bug", "feature request", "I have an idea", "something's broken".
Repository
https://github.com/kirodotdev/KiroCrew
Shell safety (READ FIRST)
Everything the user types is untrusted. Never interpolate raw user text
(titles, descriptions, search keywords) into a shell command string, and never
put it in a shell heredoc — a heredoc ends on a line equal to its delimiter,
so a body containing a line that is exactly EOF (or whatever delimiter you
pick) would terminate it early and let the following lines execute as shell.
Follow these rules for every gh invocation below:
- Body & title: write them to temp files using your own file-writing tool
(not a shell heredoc, not
echo/cat >), then feed those files togh. Create the files withmktempso the path is unpredictable and per-invocation (no fixed/tmp/...name to clobber or symlink-attack). - Pass the body with
--body-file "$BODY_FILE"(never--body "..."). - Load the title via command substitution into a double-quoted variable —
TITLE="$(cat "$TITLE_FILE")"— then pass--title "$TITLE". Command substitution assigns the text literally (it is not re-parsed as shell) and the double quotes contain word-splitting/globbing. - Search keywords: derive a few plain alphanumeric words yourself from the conversation and pass them as a double-quoted literal. Do not paste raw user text (with its punctuation/metacharacters) into the search string.
- If you cannot safely pass a value, fall back to the copy/paste option (Option 2) instead of shelling out.
Workflow
1. Greet & Identify
Ask the user what they'd like — a feature request or a bug report. Keep it casual. Don't present a form.
2. Gather Details Conversationally
Guide the user to describe:
- What they want (or what's broken)
- Why it matters (what problem it solves)
- Any context (how they hit it, what they tried)
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 · 205 lines · 43 tokens per session scan A 46b0c8c2a337
feature-request is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 1,897 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 2026-08-30.
Other skills, from other repositories
copilotkit-contribute
Use when contributing to the CopilotKit open-source project — forking, cloning, setting up the monorepo, creating branches, running tests, and submitting pull requests against CopilotKit/CopilotKit.
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…
vigilante-issue-implementation
Implement a GitHub issue end-to-end when Vigilante dispatches work for a watched repository. Use the provided worktree, respect repository instructions, comment on the issue as work progresses, and report failures back to GitHub.
vigilante-issue-implementation-on-turborepo
Implement a GitHub issue end-to-end when Vigilante dispatches work for a pnpm/workspace-based Turborepo. Use the provided worktree, respect repository instructions, comment on the issue as work progresses, and report failures back to GitHub.
vigilante-issue-implementation-on-bazel
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Bazel monorepo.
vigilante-issue-implementation-on-gradle
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Gradle monorepo.