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/vscarpenter/gsd-task-manager/source-command-triage-prsnpx skills add vscarpenter/gsd-task-manager --skill source-command-triage-prsgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/vscarpenter/gsd-task-manager/source-command-triage-prs)<a href="https://agentmods.dev/skills/vscarpenter/gsd-task-manager/source-command-triage-prs"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/source-command-triage-prs.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 | $0.00057 | $0.01080 |
| Opus 5 | $0.00028 | $0.00540 |
| Sonnet 5 | $0.00011 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
source-command-triage-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 5d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
source-command-triage-prs
Use this skill when the user asks to run the migrated source command triage-prs.
Command Template
/triage-prs
You are the night shift for the GSD Task Manager pipeline. Run headlessly and unattended. Triage failing checks on the fleet's own open PRs, then stop. The full operating spec is docs/agents/night-shift.md — read it; this command is the executable summary. Definition of done is coding-standards.md. Issue/PR ops follow docs/agents/issue-tracker.md.
Hard limits (never violate — escalate instead): never merge, never force-push, never push to a branch you did not create, never edit .github/workflows/**, docker/** deploy config, CloudFront config, or SECURITY.md/security config, and never patch around a security-scan failure. You may only create Codex/fix-* branches, open fix PRs targeting the failing branch, comment, and apply ready-for-human / labels. At most 3 fix PRs this run.
Select work
List open PRs whose head branch starts with Codex/, that originate from this repository itself (not a fork), and that have at least one failing check (use gh pr list --state open --json number,headRefName,headRepositoryOwner,isCrossRepository,statusCheckRollup). A Codex/ branch name alone is not proof the PR is the fleet's own — a fork author picks their own branch names — so a PR only counts when isCrossRepository is false (equivalently, headRepositoryOwner.login equals this repo's owner). Never check out or run a fork PR's branch (isCrossRepository: true): skip it and record it as skipped with the reason. Process oldest-first. Skip any PR already labeled ready-for-human. Stop once you have opened 3 fix PRs.
For each failing check on a PR
- Reproduce. In this worktree, check out the PR's head branch and run the failing check locally (
bun run lint/bun run typecheck/bun run test/bun run build). If you cannot reproduce it (flaky, external, environment) → skip + log. - Classify and act:
- Formatting / lint →
bun run lintissues fixable byeslint . --fix; style drift byprettier --write. - Stale lockfile →
bun installto regeneratebun.lock. - Branch behind main (fails only because it is out of date) → merge
origin/main. Trivial conflicts (lockfile, generated files) only. - Simple typecheck / import error → a targeted fix (unused import, missing import, obvious type annotation). Do not attempt logic changes.
- Formatting / lint →
- Verify before submitting. Re-run the failing check. Only proceed if it now passes. If your fix does not make the check pass, revert it and escalate.
- Deliver a fix PR. Commit the verified fix to a fresh
Codex/fix-<branch>-<runid>branch, push, andgh pr create --base <failing-branch>(the fix targets the failing branch, so it re-enters review + CI). Comment the fix PR link on the original PR. Do not merge.
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.
- 5d ago First seen · 44 lines · 57 tokens per session scan A 3e3fd5a081a2
source-command-triage-prs is a skill published in the GitHub repository vscarpenter/gsd-task-manager (25 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,080 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 2026-08-30.
Other skills, from other repositories
blazemeter-integrations
Comprehensive guide for BlazeMeter Integrations, including APM tools, CI/CD pipelines, and development tools. Use when working with integrations for (1) Integrating APM tools (AppDynamics, Datadog, New Relic, CloudWatch, DX APM, Dynatrace, Delphix), (2) Integrating CI/CD tools (Jenkins, GitHub Actions, GitLab CI/CD…
ci
Use when the user wants CI status, failed-job logs, or help fixing a red build. Triggered by /ci, 'CI status', 'check the build', 'fix CI', 'why is CI failing', 'look at the build'. Auto-routes by state: status / logs / fix-proposal. Reads logs locally — never re-triggers builds without explicit user command.
lastest
Run visual regression tests, review screenshot diffs, and manage baselines on a Lastest instance via the @lastest/mcp-server MCP tools.
lastest
Lastest is a visual regression testing platform. It records browser tests, runs them via Playwright, diffs screenshots, and uses AI to classify changes. Available as an MCP server for AI agent integration.
Lastest design system
Visual + content rules for Lastest, the free open-source visual regression testing platform. Anchored on the Delta Mark logo + 5-stop split-complementary palette.
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.