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/hermitd --skill hermit-scribegit clone --depth 1 https://github.com/gtapps/hermitdWrote 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/hermitd/hermit-scribe)<a href="https://agentmods.dev/skills/gtapps/hermitd/hermit-scribe"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/hermit-scribe/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/hermitd/hermit-scribe"><img src="https://agentmods.dev/badge/skills/gtapps/hermitd/hermit-scribe.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 | $0.00060 | $0.02398 |
| Opus 5.5 | $0.00024 | $0.00959 |
| Sonnet 5.5 | $0.00012 | $0.00480 |
| Haiku 4.5 | $0.00006 | $0.00240 |
Grade A, and why
hermit-scribe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hermit-scribe
Files a GitHub issue or posts a comment on an existing issue via a configured GitHub App bot identity.
When to activate (filing)
Activate when the operator says:
- "file PROP-NNN as a GH issue"
- "open an issue for this"
- "report this to the tracker"
- "file a GH issue for [description]"
When to activate (commenting)
Activate when the operator says:
- "add a comment to issue #NNN"
- "comment on #NNN: [text]"
- "reply to issue #NNN"
How to file
Step 1: resolve content.
If the operator named a proposal (PROP-NNN):
-
Glob
.hermit/proposals/PROP-NNN-*.mdto find the file. -
Read frontmatter:
id,title,category,session. -
Read body sections:
## Context,## Problem,## Proposed Solution,## Impact. -
Derive the Conventional-Commits type, scope, and labels. Write the raw (pre-translation) frontmatter
titleand proposal body to temp files, then run:bun "${CLAUDE_SKILL_DIR}/file-issue.ts" classify {category} {title-file} {body-file}It emits JSON
{type, scope, labels, title_line}—title_lineis<type>(<scope>): <title>(scope omitted when unresolved). Review it, then usetitle_lineas the draft title and holdlabelsfor Step 6. (Scope resolution reads_hermit_versionsfrom.hermit/config.json;hermit-filedis added by the script — it is not inlabels.) -
Construct draft body with the four body sections. The provenance footer (see Step 3) is NOT part of the draft — appending it here would expose
proposal={id}to the sanitizer, which would redact it as operator-project detail and break dedup.
For ad-hoc issues (no proposal): use the title and body the operator provides verbatim — no CC type/scope construction.
Then, for both proposal-backed and ad-hoc issues:
Step 1b: language normalization.
If the title or body is not already in English, translate to English. Preserve verbatim:
- Technical identifiers (entity IDs, API names, file paths, function names, package names, plugin slugs, repo names)
- Code blocks and command lines
- Frontmatter field names and values
- Proper nouns
What ships with it
1 file 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.
- 11d ago First seen · 210 lines · 60 tokens per session scan A a6b0106eae22
hermit-scribe is a skill published in the GitHub repository gtapps/hermitd (79 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 2,398 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 2026-10-02.
Other skills, from other repositories
implement
Implement a ticket or feature with proportional planning, test first behavior changes, independent review when available, and verification through the real affected surface.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
review-build
Review-3 (FULL) — final adversarial review of the BUILT product via a multi-agent fan-out assuming every feature is broken until a re-run check proves it (reconciliation, design+a11y, exercised rollback, observability, idempotency, secrets). Ends with a human sign-off. Two clean rounds; cap 5. Trigger after…
g-review
Run the review gate on the current branch diff. Runs the test suite, captures the diff, and dispatches code-lead, which verifies done conditions and reviews the diff itself. Issues MERGE READY or HOLD.
g-audit
Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code, and test coverage gaps. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.
g-refactor
Guided refactor workflow — identify target, pre-analyse, spec, approve, execute, review. Accepts a scope path, an audit milestone file, or runs interactively. Safe-by-default: checks test coverage before execution and runs the full review gate after.