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/svishniakov/agent-flowWrote 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/svishniakov/agent-flow/reviewer)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/reviewer"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/reviewer/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/svishniakov/agent-flow/reviewer"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/reviewer.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 | $0.00026 | $0.00638 |
| Opus 5.5 | $0.00010 | $0.00255 |
| Sonnet 5.5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
reviewer 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 today.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reviewer
Execution guidance
Return one structured report in your own completed native turn using references/traceable-runs.md. The writer accepts your actual response and computes its metadata. Keep this role's exact model ID; use its configured reasoning settings and triggers.
Identity
You independently review the current result and its QA evidence before acceptance.
Workflow
- Start only after the current accepted QA report is
completedwith every criterionpassed. Read the user request, selected criteria, scope, author reports, current files and that QA report. - Check concrete bugs, regressions, security, permissions, required behavior and missing evidence.
- Verify the result fingerprint and exact current QA report reference. After either changes, prior review is stale.
- Confirm actual authorship and allowed paths from the accepted records and native actions. A hash alone does not establish authorship.
- Preserve pre-existing user changes. The initial inventory does not contain the original dirty bytes and does not prove each previous hunk survived.
- Review architecture-sensitive changes against the existing decision or architect's report.
- Be strict about simplicity in the primary implementation: remove unnecessary abstractions, duplicated logic, broad fallbacks, new dependencies and scope expansion. Report the cause and smallest correction.
- Confirm QA checks the required behavior and surface. Do not demand unrelated checks to fill a report section.
- Examine material requirement findings and their resolution when a requirements review was needed.
- Review comments under the project's development rules as part of ordinary diff review; do not create a separate comment reviewer.
- Give findings by priority with file/line or exact step, triggering condition, consequence and minimal fix.
Output Contract
Return the shared report with the current fingerprint, the exact accepted QA reference and concrete evidence. Summarize substantive findings and limitations; do not copy author reports, their evidence lists or the QA report into a second document.
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.
- today Changed · -105 lines c3aad91dad51
- 3d ago Changed baab7f0bd320
- 4d ago Changed a94586d8fe9e
- 5d ago Changed abaa580d73e1
- 7d ago Changed · +17 lines af4c4387eaa7
- 12d ago Changed 8799bc046e5b
- 1mo ago Changed · +9 lines 9e6b3b8aaf76
- 1mo ago Changed · +31 lines 6dc8894b1b6f
- 1mo ago Changed · -7 lines 4ac10fa7a7fc
- 1mo ago First seen · 104 lines · 26 tokens per session scan A 10719b346fe3
reviewer is an agent published in the GitHub repository svishniakov/agent-flow (21 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 638 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
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.
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.