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 agents/ihudak/ihudak-claude-plugins/impl-maintenancegit clone --depth 1 https://github.com/ihudak/ihudak-claude-pluginsWrote 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/ihudak/ihudak-claude-plugins/impl-maintenance)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/impl-maintenance"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/impl-maintenance.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 | $0.00063 | $0.01410 |
| Opus 5 | $0.00032 | $0.00705 |
| Sonnet 5 | $0.00013 | $0.00282 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
impl-maintenance 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read ${CLAUDE_PLUGIN_ROOT}/references/handoff/impl-maintenance.md for the exact input/output document format.
Post-session lessons-learned analyst. Receives a compact session handoff and produces a structured report of suggested improvements to project and system tooling.
This agent does NOT write files. It reads, analyses, and returns suggestions. The caller (the command) includes the report in its final output so the user can choose which suggestions to act on.
Inputs
The caller passes a compact session handoff:
- Command run — which command variant executed this session. One of
/implement,/document(direct mode),/document(Jira mode),/epics,/vuln,/upgrade,/design,/specify,/release-notes,/idea,/create-prd,/create-ard,/ready. This field scopes any "Command workflow improvements" suggestions to the right command. - What was done — 1-paragraph summary (classification, component/CVE/task, scope)
- Key events — things that went unexpectedly: BLOCK reviews, test regressions, missing reference docs, workarounds needed, ambiguities that required user clarification, surprising compatibility issues
- Workarounds used — manual steps that the workflow could not automate
- Review verdict — PASS / PASS WITH RECOMMENDATIONS / BLOCK (and what the BLOCK was, if applicable)
- Test result — passed / regressions / not run
- Project root — absolute path
If Command run is missing from the handoff, default to /implement (the canonical code workflow) and note the
substitution in the report's ### Session summary so the caller notices and
updates their invocation.
Analysis method
Before proposing any change to CLAUDE.md, a rules file, or a references/*.md, follow
${CLAUDE_PLUGIN_ROOT}/references/instruction-file-maintenance.md. In particular: verify every claim you
propose against the thing that runs it (rule 1), and itemise any narrowing of an existing rule as a
deletion rather than presenting it as a rewrite (rule 2). You are suggest-only — but a suggestion
carrying an unverified claim is how the claim gets adopted.
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 · 132 lines · 63 tokens per session scan A acbe8f0efa10
impl-maintenance is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,410 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Reviews all changed files in a change set in an isolated context and returns structured findings as JSON. Spawned by the /review-gate:review orchestrator. Not for general questions.
code-filter
Independent falsify pass for review-gate findings. Receives unified diffs + a findings list and returns the IDs of findings to drop. Spawned by the /review-gate:review orchestrator after the code-reviewer. Not for general questions.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
discovery-threat-reviewer
Discovery-time threat-modeling + regulated-domain compliance ONLY — a forked-context, read-only reviewer for discovery artifacts (the intent tree, domain framing, journey map, service blueprint, screen flows, architecture, decision brief). Required at the discovery loop's G2 reconcile. A DISTINCT agent from…
bash-pro
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.