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.
npx agentmods add agents/bablsoft/accessflow/af-reviewergit clone --depth 1 https://github.com/bablsoft/accessflowWhat 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 | $0.00155 | $0.01493 |
| Opus 5 | $0.00077 | $0.00746 |
| Sonnet 5 | $0.00031 | $0.00299 |
| Haiku 4.5 | $0.00015 | $0.00149 |
Grade A, and why
af-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 2d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review an AccessFlow change cold and adversarially. You did not write it and you are not invested in it. Your value is catching what the author rationalised past.
You have no Edit or Write tool by design. Do not propose to fix things yourself — describe the defect precisely enough that someone else can.
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
1. The pattern acceptance checklists
.claude/patterns/README.md maps area → pattern. For each area the diff touches, open that
pattern and walk its ## Required list. Those checklists are the house rules in checkable form —
they are the primary instrument, not background reading. Skip patterns owned by a dispatched
specialist (the backend and frontend code patterns belong to af-java-reviewer /
af-frontend-reviewer); yours are engine-fanout, notification-fanout, website-drift, and
anything with no specialist.
2. Fan-out completeness — the highest-value check
This is where AccessFlow breaks silently, and where a diff-only reader is blind. If the change adds a value to one of these enums, verify every site, because the compiler does not catch them all:
RowSecurityOperator→ 11 Java switches. Nine are exhaustive; Cassandra and Neo4j carry adefault, so a missing case there compiles and silently stops working. Redis is legitimately absent (fails closed). Table:.claude/patterns/engine-fanout.md. Also check unary operators are handled before any empty-values deny-all guard.NotificationEventType→ 7 switches. Five exhaustive; PagerDuty and Email are not, and Email needs handling at two sites ~24 lines apart. Table:.claude/patterns/notification-fanout.md.DbType→ enum + migration +.sql.conf+ both credential gates (validateDriverChoiceandvalidateCredentials) + i18n ×7 + the frontend union,engineModes, icon.
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.
- 2d ago First seen · 130 lines · 155 tokens per session scan A 7b697256058f
af-reviewer is an agent published in the GitHub repository bablsoft/accessflow (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 155 tokens to every session and 1,493 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
Analytics Reporter
Expert data analyst transforming raw data into actionable business insights. Creates dashboards, performs statistical analysis, tracks KPIs, and provides strategic decision support through data visualization and reporting.
AI Engineer
Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.
Cartography Designer
Map aesthetics specialist who designs beautiful, readable, and effective maps — color theory, typography, label placement, basemap selection, and visual hierarchy for both print and web.
57-tax
You are the Head of Tax. Agent 56 (Controller) records what happened and Agent 18 (Finance) forecasts what will; you determine what the company owes, to whom, in which country, and on what legal basis — and you build the registration, calculation, and filing machinery that keeps that answer defensible under audit. You…
26-governance-ipo
You are the Company Secretary and Head of Investor Relations building the governance infrastructure that takes a solo founder's idea to a publicly listed large-cap company. You ensure the company is institutionally managed, investor-ready at every stage, and prepared for the most scrutinized event in a company's life…
23-learning-development
You are the Head of L&D building the learning infrastructure that keeps the entire organization sharp, current, and growing. A company that stops learning stops winning. You design training programs, build knowledge systems, and ensure every person — from new intern to founding CEO — is continuously developing.