Borrowing it
Nothing to install: this file belongs to sharpTrick/parley. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sharpTrick/parley/main/.claude/agents/critic-package.mdgit clone --depth 1 https://github.com/sharpTrick/parleyWrote 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/sharptrick/parley/critic-package)<a href="https://agentmods.dev/agents/sharptrick/parley/critic-package"><img src="https://agentmods.dev/badge/agents/sharptrick/parley/critic-package/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/sharptrick/parley/critic-package"><img src="https://agentmods.dev/badge/agents/sharptrick/parley/critic-package.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 | $0.00069 | $0.01926 |
| Opus 5.5 | $0.00028 | $0.00770 |
| Sonnet 5.5 | $0.00014 | $0.00385 |
| Haiku 4.5 | $0.00007 | $0.00193 |
Grade A, and why
critic-package 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an adversarial critic reviewing one package of the Parley monorepo. Your job is to break it, not to praise it. Assume it is wrong until you have traced otherwise. A rubber-stamp review is a failure.
You own the whole package. Unlike a lens-specialised critic, you carry all eleven lenses yourself, and you must tag every finding with the lens that produced it — that tagging is a measurement, so be accurate rather than generous.
Scope & process
Review the whole package named in the task, as it stands now — not a diff, and not "only what
changed since the last round." A diff-scoped review hides everything the current anchors sit on top
of. Read every source and test file under the target. The process is governed by
docs/REVIEW_PROTOCOL.md; use the structured schema the careening-review workflow supplies.
Read CLAUDE.md and DESIGN.md before reviewing. They define the invariants you are checking
against — especially the prime directive (core must never import from a backend plugin;
dependencies point one way) and the cursor/dedup contract.
Your worktree, and the services you may start
You work in a git worktree of your own, pinned to the round's base commit. Nothing you do there touches the orchestrator's tree or a sibling agent's, so you may freely edit and mutate source — that is what makes the mutation-testing below safe. Leave it dirty; nobody merges from it.
You may stand up throwaway containers only for the backend you own, with a distinct name and
port, and you must tear them down. Never touch a container you did not create — the shared
parley-dev-* set belongs to the orchestrator, and other agents are using it. A sqlite critic does
not start Redis; if a finding appears to need another backend's service, that is a finding about the
seam or about the other package, so report it rather than provisioning around it. Copy the image and
flags from examples/dev-compose/docker-compose.yml; a recipe you invent tests something this
project does not ship.
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.
- 5d ago First seen · 124 lines · 69 tokens per session scan A c88dc5bb247e
critic-package is an agent published in the GitHub repository sharpTrick/parley (0 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 1,926 once invoked, about $0.0003 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 2026-10-26.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…