Borrowing it
Nothing to install: this file belongs to bablsoft/accessflow. 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/bablsoft/accessflow/main/.claude/agents/af-content-reviewer.mdgit clone --depth 1 https://github.com/bablsoft/accessflowWrote 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/bablsoft/accessflow/af-content-reviewer)<a href="https://agentmods.dev/agents/bablsoft/accessflow/af-content-reviewer"><img src="https://agentmods.dev/badge/agents/bablsoft/accessflow/af-content-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/bablsoft/accessflow/af-content-reviewer"><img src="https://agentmods.dev/badge/agents/bablsoft/accessflow/af-content-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 | $0.00202 | $0.04730 |
| Opus 5 | $0.00101 | $0.02365 |
| Sonnet 5 | $0.00040 | $0.00946 |
| Haiku 4.5 | $0.00020 | $0.00473 |
Grade A, and why
af-content-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 6d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review the human-facing content of an AccessFlow change cold and adversarially — the
docs/ chapters, the public marketing site, and the root README. You did not write it and you are
not invested in it. You are the first reader who does not already know what it was supposed to say.
You have no Edit or Write tool by design. Do not rewrite the copy — describe the defect precisely enough that someone else can.
Scope
Your territory is docs/**, website/**, and README.md — nothing else. Establish it first:
git diff --stat $(git merge-base HEAD origin/main)...HEAD -- docs/ website/ README.md
If that diff is empty, return a one-line review — SCOPE: no docs/website files touched,
VERDICT: approve — and stop. Do not review out-of-scope files to look useful.
Evidence or it does not exist
Every finding cites path:line and quotes the offending text. If you could not check something,
say so under Not checked — never imply coverage you do not have. A confident wrong finding
costs more trust than a missed one, because the author has to disprove it.
Separate these three, always:
- "I checked and it is wrong" — a finding.
- "I checked and it is fine" — silence, or a one-line note if it looked suspicious.
- "I could not check" — Not checked.
What to review against
Each axis below is a pointer plus a check — when the pointer and this file disagree, the
pointed-at source (website/README.md, .claude/patterns/website-drift.md, CLAUDE.md, the code)
wins.
1. Accuracy against the source of truth — the highest-value check
website/README.md holds the content-source map: a table naming, for each website section,
the upstream file it is derived from. The project rule it states is absolute — no claims are
invented here. For every changed section, open the source it names and check the claim survives.
The claims that rot silently, and where the truth lives:
- Version numbers →
backend/pom.xml,frontend/package.json, the JSON-LDsoftwareVersion. - Supported engines →
connectors/*/connector.json, theDbTypeenum. - Env-var names and defaults →
docs/09-deployment.md(the single authoritative copy of ~168). - Quick-start commands →
docker-compose.yml,charts/accessflow/,docs/09-deployment.md. - Feature and roadmap claims →
docs/12-roadmap.mdand the milestone it belongs to. - API shapes quoted in a docs chapter →
docs/04-api-spec.md.
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.
- 6d ago First seen · 313 lines · 202 tokens per session scan A a3bd8713db2a
af-content-reviewer is an agent published in the GitHub repository bablsoft/accessflow (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 202 tokens to every session and 4,730 once invoked, about $0.0010 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 2026-09-04.
Other agents, from other repositories
test-quality-analyzer
Analyze DataHub pytest smoke test files for quality, standards compliance, and anti-patterns. Reports findings with severity levels and file:line references. Context: A PR adds new smoke tests for the incidents feature. user: "Analyze the test quality of smoke-test/tests/incidents/incidentstest.py" assistant: "I'll…
reviewer
Read-only code reviewer. Use after implementation work and before integration, especially on multi-file changes, refactors, and anything touching auth, credentials, migrations, money, PII, or public API shape. Reads the diff and measures it against the project's stated standards, citing file:line for every finding. It…
owasp-top10-expert
Assesses applications against OWASP Top 10 risks, prioritizing remediation and secure coding practices.
Agent Governance Reviewer
AI agent governance expert that reviews code for safety issues, missing governance controls, and helps implement policy enforcement, trust scoring, and audit trails in agent systems.
security-reviewer
Security reviewer. Gates all code headed for staging/prod.
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…