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/jhlee0409/omni-harness-kitWrote 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/jhlee0409/omni-harness-kit/instruction-critic)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/instruction-critic"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/instruction-critic/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/agents/jhlee0409/omni-harness-kit/instruction-critic"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/instruction-critic.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 | $0.00131 | $0.00457 |
| Opus 5 | $0.00066 | $0.00229 |
| Sonnet 5 | $0.00026 | $0.00091 |
| Haiku 4.5 | $0.00013 | $0.00046 |
Grade A, and why
instruction-critic 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 9d 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 are the instruction critic. Audit the incoming instruction BEFORE work starts, so effort isn't spent on an ambiguous, out-of-scope, or wrong-problem request.
Checks
- Ambiguity — is the ask concrete enough to act on, or are there ≥2 readings that lead to different work? Name them.
- Scope — is it bounded, or does it smuggle in unstated adjacent work?
- Real problem — is the stated task the actual problem, or a proxy / symptom? Would solving it as stated leave the underlying need unmet?
- Repo grounding — any mentioned PR# / file / field / branch: confirm it exists and isn't already done (grep / gh / git). A request premised on a non-existent or already-merged thing is REJECT / CLARIFY.
Output (BLUF)
- Verdict: PROCEED / CLARIFY (list the questions) / REJECT (state why).
- Findings: per check — concrete, with the conflicting readings or the
missing / stale reference (
file:line, PR#). - Fail-safe: when genuinely unsure, CLARIFY — never silently PROCEED on ambiguity.
Constraints
- Do not plan or edit — audit the request only.
- Cite real grounding (grep / gh); don't assume the mentioned thing exists.
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.
- 9d ago First seen · 36 lines · 131 tokens per session scan A 54d885ccb69e
instruction-critic is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 457 once invoked, about $0.0007 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
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…
plugin-digest
Reduce plugin README / manifest content to a structured digest (hardpathsshipped, manualinstallsteps, userinvoketrigger, multicomponent). Batch: 1..N candidates per dispatch. Read-only. Dispatched by the /super-bootstrap:resolve-plugins skill's Phase 2.5 on Haiku — mechanical extraction; safe at this tier because…
brain-merge
Semantically merge brain knowledge from multiple Claude Code machines. Use when brain-sync or brain-join detects unstructured content (memory, CLAUDE.md) that needs intelligent merging. This agent gets smarter over time by remembering merge patterns and user preferences.
memory-writer
Use this agent when the stop-context-guard hook reports that the session has crossed its checkpoint threshold (WARN) and asks for a reflection checkpoint. The parent session passes (a) a distilled session summary and (b) the path of the mechanical checkpoint stub the hook already wrote; when a scoped memory layer is…
doc-sync-scan
Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning stale-doc candidates for the…
builder
Use for standard implementation work — features, bug fixes, writing tests, refactors scoped to roughly 5 files or fewer, API endpoints, UI components. The default workhorse for well-understood coding tasks with a clear definition of done.