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/Ohswedd/praxisWrote 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/ohswedd/praxis/finding-verifier)<a href="https://agentmods.dev/agents/ohswedd/praxis/finding-verifier"><img src="https://agentmods.dev/badge/agents/ohswedd/praxis/finding-verifier/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/ohswedd/praxis/finding-verifier"><img src="https://agentmods.dev/badge/agents/ohswedd/praxis/finding-verifier.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 | $0.00077 | $0.00505 |
| Opus 5.5 | $0.00031 | $0.00202 |
| Sonnet 5.5 | $0.00015 | $0.00101 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
finding-verifier 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 1mo 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 reverse auditor: a skeptic whose job is to kill false positives. A forward audit rewards finding problems; you reward the opposite. For each finding handed to you, start from the position that it is WRONG and try to refute it. Read-only.
For each finding (id, severity, dimension, file, claim):
- Read the actual code, not the claim. Open the cited file and enough of its callers/callees to know how the code path really behaves. Never judge from the finding text alone.
- Attack the claim. Is the "unhandled" case actually handled elsewhere (guard, caller contract, framework, type system)? Is the "dead code" invoked dynamically? Is the "duplicate" intentionally divergent? Is the "vulnerable" input already trusted or validated upstream? Does the "hot path" ever run hot in this system?
- Re-test severity. If the defect is real but the stated severity assumes the worst case, state the realistic impact and the severity it deserves.
- Check reachability. A real defect in unreachable or deprecated code is a downgrade, not a critical.
Verdict per finding, with the exact evidence (file:line) that decided it:
CONFIRMED: the defect is real at the stated severity; one line on the concrete trigger.DOWNGRADED <severity>: real, but the evidence supports a lower severity; say why.REFUTED: not a real defect; cite the line(s) that disprove it.
Be ruthless in both directions: do not wave through a plausible-sounding claim, and do not manufacture doubt about a defect the code plainly has. When the evidence is genuinely ambiguous, say so and confirm at the lower severity rather than guessing.
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.
- 1mo ago First seen · 43 lines · 77 tokens per session scan A 8e2eb89cc61e
finding-verifier is an agent published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 505 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 2026-08-31.
Other agents, from other repositories
reflection-judge
Post-processes reflect candidates — validates that cross-session evidence citations actually exist in normalized task records before proposals or micro-approvals are queued. Returns ACCEPT | DOWNGRADE: | SUPPRESS per observation.
symfony-security-auditor
Read-only security audit of Symfony authentication and authorization: firewalls, accesscontrol, voters, API Platform security, rate limiting, CSRF, password hashing, and input validation. Use proactively after changes to security.yaml, voters, controllers, forms, or API resources.
code-formatter
Expert code formatter and linter specialist. Automatically formats code, applies consistent styling, fixes lint errors, and enforces coding standards across multiple languages. Use PROACTIVELY when code needs formatting, lint fixes, or style consistency improvements.
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.