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 zookanalytics/gc-toolkit --skill prsgit clone --depth 1 https://github.com/zookanalytics/gc-toolkitWrote 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/zookanalytics/gc-toolkit/prs)<a href="https://agentmods.dev/skills/zookanalytics/gc-toolkit/prs"><img src="https://agentmods.dev/badge/skills/zookanalytics/gc-toolkit/prs/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/zookanalytics/gc-toolkit/prs"><img src="https://agentmods.dev/badge/skills/zookanalytics/gc-toolkit/prs.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 | $0.00106 | $0.02019 |
| Opus 5.5 | $0.00042 | $0.00808 |
| Sonnet 5.5 | $0.00021 | $0.00404 |
| Haiku 4.5 | $0.00011 | $0.00202 |
Grade A, and why
prs 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRs: what happens to an open pull request
An open pull request is tracked by its anchor, the bead whose merge_result is
pull_request. The refinery's reconcile reads the PR and its anchor every pass
and lands the PR once it is approved and nothing holds it. Each option says what
the message means, who acts on it, and the one writer that sends it. The
writer's --help carries its flags.
The writers are the gc-toolkit pack's own scripts.
gc <binding> scripts-dir prints their directory in the pack as gc loaded it,
so each example calls the pack's copy inside the command itself, and runs in a
fresh shell. <binding> is the name the city imports the pack under, which gc
puts in front of this skill's name: gc-toolkit in gc-toolkit.prs.
gc skill list prints it in this skill's FROM column.
Answer its review comments
The message is the city's answer to a reviewer: a fix that landed, an answer to a question, or a decision. The reviewer reads it, and the reconcile reads it as the city's own post rather than new feedback.
Writer: pr-post.sh, the only way the pack posts on a pull request.
- A reply in a review thread:
"$(gc <binding> scripts-dir)/pr-post.sh" reply --host github.com --thread <the thread's PRRT_ id> --body-file <file>. - A conversation comment:
"$(gc <binding> scripts-dir)/pr-post.sh" comment --repo github.com/<owner>/<name> --pr <number> --body-file <file>.
It appends the city's mark. The reconcile reads a post without that mark as new
feedback and routes it into rework, so never post with gh directly.
A rework that answers a review's findings posts no answer of its own. It records
each answer with finding.sh answer, as its work order says, and the city's one
living comment per review shows the reviewer how each point was answered. A
reply through pr-post.sh only adds detail that answer leaves out.
Resolve a thread only once its answer has landed. The write-back resolves a
thread whose fix a rework landed. A thread you answered yourself, with nothing
left to land, you resolve with GitHub's resolveReviewThread mutation on the
thread's PRRT_ id:
gh api graphql -f query='mutation($t:ID!){resolveReviewThread(input:{threadId:$t}){thread{isResolved}}}' -f t=<PRRT_ id>.
Leave a thread open when a person replied in it after you, or when it holds a
declined, deferred or needs-you point, because a person closes those.
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 · 146 lines · 106 tokens per session scan A 78953d14032d
prs is a skill published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 2,019 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy; the ship recipe also executes PR delivery (create, CI watch, merge, cleanup) with Ask First on merge. Use when PR preparation, commit strategy, or gated PR delivery is needed.
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
harness-pr-reviewer
Checks a submitted PR against the environment's baseline assets (CLAUDE.md, memory, naming, asset classification) and attaches a review comment with a merge recommendation. 5 steps — diff read, 8-area consistency check, self-catch, comment, merge recommendation.
ai-driven-code-editor-cli
OpenCode AI - AI-driven code editor/IDE (CLI/TUI version of Cursor/Windsurf). Use when: (1) AI-assisted coding tasks, (2) Code refactoring with AI, (3) GitHub PR review/fixes, (4) Multi-file edits requiring context, (5) Running AI agents on codebases. NOT for: simple one-line ed…
pr-check
PR review compliance: fetch review comments from an open PR, categorize as resolved/unresolved/dismissed, critically evaluate fixable items, implement approved fixes, and reply inline. Pass --unattended to halt on human-judgment items (emitted as Pending-Human) instead of prompting via AskUserQuestion.