Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jackchuka/ghpmnpx agentmods add skills/jackchuka/ghpm/ghpm-workWrote 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/jackchuka/ghpm/ghpm-work)<a href="https://agentmods.dev/skills/jackchuka/ghpm/ghpm-work"><img src="https://agentmods.dev/badge/skills/jackchuka/ghpm/ghpm-work/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/jackchuka/ghpm/ghpm-work"><img src="https://agentmods.dev/badge/skills/jackchuka/ghpm/ghpm-work.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 | $0.00052 | $0.00853 |
| Opus 5.5 | $0.00021 | $0.00341 |
| Sonnet 5.5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
ghpm-work 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ghpm-work
PREREQUISITE: Read
../ghpm-shared/SKILL.mdfor prerequisites and error handling.
End-to-end workflow for a GitHub Project item. /ghpm-work <issue-number> drives the full lifecycle.
If no argument, ask for the issue number.
Flow
Setup → Clarify → Plan → Implementation Plan → Implement → Draft PR
↕ decisions captured at every phase ↕
| Phase | Reference | What happens |
|---|---|---|
| 1. Setup | references/setup.md |
Resolve item, assign, branch, status sync, write session |
| 2. Clarify | references/clarify.md |
Evaluate issue clarity, flesh out if needed, gather context |
| 3. Plan | references/plan.md |
Explore codebase, draft approach, post as issue comment |
| 4. Impl Plan | references/implementation-plan.md |
Concrete steps, files, tests — post as issue comment |
| 5. Implement | references/implement.md |
Execute plan, write code, commit, verify |
| 6. Draft PR | references/draft-pr.md |
Create draft PR with summary |
Decisions: See references/decisions.md. Capture at ANY phase — not just coding. Watch every interaction for choices worth recording.
Wrap up: See references/wrap-up.md. Triggered by "wrap up" or "done".
Session Resume
Sessions track phase in .ghpm/sessions/<number>.json (schema in ../ghpm-shared/references/session.md).
Each phase writes its phase value to the session file on entry, before doing any work. This means on resume, re-run the recorded phase (it may have been interrupted):
phase |
Resume from |
|---|---|
missing/setup |
Clarify (setup completed, phase field not yet added) |
clarify |
Clarify |
plan |
Plan |
implementation_plan |
Implementation Plan |
implement |
Implement |
pr |
Draft PR |
done |
Session complete — inform user and stop |
On resume, briefly show what's already done before continuing.
Prompt Configuration
Per ../ghpm-shared/references/prompts.md. This skill's config lives at prompts.ghpm-work in .ghpm/config.json.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 80 lines · 52 tokens per session scan A 72f60b66f151
ghpm-work is a skill published in the GitHub repository jackchuka/ghpm (20 stars, last pushed 10d ago), licensed MIT. It adds 52 tokens to every session and 853 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
git-issue-triage
Groom an open GitHub backlog with gh - one read-only sweep, every open issue bucketed into exactly one category (unlabeled, unprioritized, stale, likely duplicate, closeable, blocked, healthy), a per-issue report, per-category confirmation, then batched label / state / comment edits. Use when the user says "triage…
git-issue-create
Open one standalone GitHub issue with gh - duplicate-checked first, conventional title, repo-template-aware body, auto-resolved labels. Use for every issue-filing request however casual: "open an issue", "file a bug", "make a ticket", "/git-issue-create", "track this", "note this down", "we should fix X later", or…
git-issue-start
Take a GitHub issue from open to a checked-out branch - assign it to you, mark it in progress if the repo has such a label, derive a conventional branch name from its type: label, branch off the detected base. Use for "start issue 42", "work on #42", "/git-issue-start 42", "let's do 42", "pick up that issue", "take…
airtable-automation
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
360-feedback-system
360 feedback register: reviewer, subject, review cycle, visibility, due date and score, as CSV, SQL, JSON Schema or Notion on request. Use for 360 reviews or peer feedback cycles.
alumni-re-hire-tracker
Alumni and re-hire register: former role, last working day, re-hire eligibility, current employer and re-engagement date, as CSV, SQL, JSON Schema or Notion on request. Use for alumni outreach.