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 gtapps/claude-code-hermit --skill tackle-issuegit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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/gtapps/claude-code-hermit/tackle-issue)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/tackle-issue"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/tackle-issue/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/gtapps/claude-code-hermit/tackle-issue"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/tackle-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00149 | $0.02478 |
| Opus 5.5 | $0.00060 | $0.00991 |
| Sonnet 5.5 | $0.00030 | $0.00496 |
| Haiku 4.5 | $0.00015 | $0.00248 |
Grade A, and why
tackle-issue 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tackle-issue — 88% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tackle Issue
Triage first, then optionally set up the work. Read-only until the operator picks "go" at the end. Implementation, commit, and PR happen outside this skill.
Mindset
An issue or proposal is a hypothesis, not a spec. Most issues here are filed by AI agents (hermit-scribe): intent is usually right, framing often is not (stale paths, first-idea fix, oversized scope, premise already fixed, or no bug at all). Falsify the premise before planning anything. If it survives, judge separately whether the change is worth its cost.
Two failure modes, both disqualifying:
- Rubber-stamping: implementing exactly what was written when a simpler fix exists or the premise is partly wrong.
- Reflex-pushback: manufactured objections. If the premise holds and ROI is good, say "ship as written" plainly.
Proportionality: scale investigation to blast radius. A one-file doc fix needs falsification steps 1 and 3 only, and a two-line trade-off note. Anything touching hooks, shipped skills, or release machinery gets the full pass, including a live probe when a harness-behavior claim is load-bearing.
Dispatch
- Issue number ("tackle issue 99", "#42", "owner/repo#N"):
gh issue view <N> --repo <owner/repo from input, default gtapps/claude-code-hermit> --json title,body,labels,comments,author,state,urlRead the comments: they often say "already fixed" or change scope, and they override the body. Pull referenced issues/PRs when the body leans on them. Closed issue → surface that and ask before continuing. Also rungh pr list --repo <repo> --state open --search "<N>": an open PR already covering the issue usually means DEFER to that PR. - Pasted content (proposal, spec, free-form): treat the text as the task body. Triage output only, no handoff.
- Picker ("tackle the next issue", "what should I work on", bare
/tackle-issue): run Picker below, then continue as issue-number mode. - Ambiguous ("tackle this", no number, no paste): ask which mode before fetching anything.
--investigate-only(combines with issue-number mode): full triage report including the plan sections on positive verdicts, then stop. No branch, no tasks.
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 Changed 8c3687a141b4
- 1mo ago Changed 6301d9baa878
- 1mo ago Changed f2377d85c7f2
- 1mo ago First seen · 206 lines · 149 tokens per session scan A 63026c6a6790
tackle-issue is a skill published in the GitHub repository gtapps/claude-code-hermit (81 stars, last pushed yesterday), licensed MIT. It adds 149 tokens to every session and 2,478 once invoked, about $0.0006 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
pave-catalog
Build a service catalog — schema, starter entries, and governance model. Produces what information to capture per service, how it's maintained, and where it lives. Use when asked to "service catalog", "what services do we have", "catalog our services", "service inventory", or "who owns what".
atlas-present
Generate a polished HTML presentation page and Obsidian Canvas for big releases — new products, takeovers, major migrations. Non-technical audience. Use when asked to "present this", "release announcement", "show what we built", or "stakeholder update".
crest-okr
OKR design — create objectives and key results with a North Star metric, input metrics tree, and cadence. Use when asked to "set OKRs", "define our objectives", "what should we measure this quarter", "design our OKR framework", "build a metrics tree", or "what's our North Star".
crest-narrative
Strategic narrative — write a standalone strategy memo that frames product direction, bets, and rationale for a planning horizon. Use when asked to "write a strategy doc", "product vision", "strategic narrative", "company strategy memo", "planning memo", or "explain our product direction".
crest-recon
Strategic context reconnaissance — read existing roadmaps, OKRs, competitive docs, and briefs to establish context before planning. Use when asked to "understand our strategy", "what's the current roadmap", "what OKRs do we have", "strategic context", or before starting any prioritization or roadmap work.
apex-recon
Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.