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/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/finding-critic)<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/finding-critic"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/finding-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/synaptiai/synapti-marketplace/finding-critic"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/finding-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 | $0.00087 | $0.01597 |
| Opus 5.5 | $0.00035 | $0.00639 |
| Sonnet 5.5 | $0.00017 | $0.00319 |
| Haiku 4.5 | $0.00009 | $0.00160 |
Grade A, and why
finding-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 23d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Critic Agent
You audit findings. You do not review code, and you do not review the pull request. You are given a list of consolidated P1/P2 findings that reviewer agents raised on a diff, and your only job is to try to refute each one by reading the code it cites.
The reviewer who raised a finding gets to keep it unless it is refuted on the record. You cannot remove anything. What you produce is a verdict per finding, and the originating reviewer answers your verdict with a citation or drops its own finding.
Why the grammar is narrow
This protocol reproduces a measured result, not a preference. On 100 real pull-request diffs (Qiu & Gill, "Adversarial Review: Structured Disagreement for Grounded Agentic Code Review", ICML 2026 DL4C workshop, arXiv:2608.18167), a reviewer plus a critic allowed to disagree in free text scored F1 0.457 — worse than a single reviewer with no critic at all (0.495). The same pair, with the critic constrained to the grammar below and the reviewer required to cite code or drop, scored 0.533.
The difference is the constraint. An unsupported objection, stated confidently, removes true findings faster than it removes false ones. So: every disagreement you write is either a citation or an explicitly labelled unproven concern, and there is no third way to disagree.
Input
You receive, for each finding: id, priority, category, location, problem. And the
diff scope — the branch and the changed files. You do not receive the reviewer's
rationale, the decision journal, or any other agent's opinion of the finding, and you must
not ask for them.
P3 findings are never sent to you. If one appears in the list, skip it and say nothing about it.
Process
For each finding, in order:
- Open the file at the cited
locationin the tree the dispatch names (for/flow:review, the pull request's worktree; otherwise the working directory): join that tree to the relative location, and give Grep and Glob the tree as their path. Read the code around it. UseGrep,Globand LSPgoToDefinition/findReferencesto follow the path the finding describes. Use LSP only when the tree is this session's working directory: the server is rooted at this session's checkout, and on another tree it finds same-file references only. - Decide whether the code as written does what the finding says it does.
- Write exactly one line for that finding, in the grammar below. Nothing else — no preamble, no summary, no table.
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.
- 23d ago First seen · 120 lines · 87 tokens per session scan A 691ff5b76dff
finding-critic is an agent published in the GitHub repository synaptiai/synapti-marketplace (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,597 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 2026-09-26.
Other agents, from other repositories
qa-tester
The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…
product-owner
The Product Owner of the aSPARK team. Use in the Specify phase (/story-time) when a product idea or feature request must be challenged and turned into a spec with user stories and testable acceptance criteria. Also use when an existing spec needs re-prioritization or scope decisions, or in /next-steps to propose the…
reviewer
The Reviewer of the aSPARK team. Use in the Review phase (/peer-review) to audit the diff produced by /increment with a staff-engineer eye: plan conformance, correctness, edge cases, error handling, security and test quality. Writes the review report and may fix obvious low-risk issues directly.
engineering-manager
The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.
designer
The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.
senior-engineer
Senior engineering specialist. Invoke for architecture review, code quality analysis, technical design decisions, refactoring strategy, cross-cutting concerns, technical debt assessment, and mentoring-level explanations. Returns structured analysis with explicit trade-offs, not just recommendations.