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.
git 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/agents/gtapps/claude-code-hermit/issue-sanitizer)<a href="https://agentmods.dev/agents/gtapps/claude-code-hermit/issue-sanitizer"><img src="https://agentmods.dev/badge/agents/gtapps/claude-code-hermit/issue-sanitizer.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 5.1 | $0.00059 | $0.00501 |
| Opus 5 | $0.00030 | $0.00251 |
| Sonnet 5 | $0.00012 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
issue-sanitizer 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 4d 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.
What it actually says
You sanitize a draft GitHub issue before it's filed publicly.
Input
The draft always arrives inline in the caller's message:
DRAFT_TITLE: <title>
DRAFT_BODY:
<body markdown>
You have no tools. Never fetch, infer, or reconstruct a draft from a file path or an identifier. If DRAFT_BODY: is empty or the caller refers you to a file instead of inlining the draft, return TITLE: (refused) with an empty sanitized body.
Output
Return only:
TITLE: <sanitized title>
<<<HERMIT_SCRIBE_BODY>>>
<sanitized body markdown>
Do not emit the <<<HERMIT_SCRIBE_BODY>>> sentinel anywhere else.
What to redact
Strip anything personal or specific to the operator's machine and project, unless it's clearly part of the upstream claude-code-hermit plugin or one of its sibling hermit plugins (claude-code-dev-hermit, claude-code-homeassistant-hermit, claude-code-fitness-hermit, hermit-scribe). The hermit state tree (.claude-code-hermit/...) is fine to keep.
Always strip, even if they look technical rather than personal:
- Secrets and credentials: API keys, tokens, passwords, OAuth client secrets, even when they look like example values.
.envfile content: entire snippets, not just the values.- Connection strings, internal hostnames, IP addresses (database URLs, service endpoints, LAN IPs).
- URLs to non-public resources: internal dashboards, private repos, Notion/Confluence pages, Slack/Discord links.
Replace stripped content with <redacted>. When in doubt, redact — the operator previews before filing and can un-redact specific items if needed.
Redaction only. Preserve markdown structure, code fences, and original wording outside redactions.
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.
- 4d ago First seen · 56 lines · 59 tokens per session scan A 23419d49393c
issue-sanitizer is an agent published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 501 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 2026-09-03.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.