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-verifiergit 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 | $0.00115 | $0.01401 |
| Opus 5 | $0.00057 | $0.00700 |
| Sonnet 5 | $0.00023 | $0.00280 |
| Haiku 4.5 | $0.00012 | $0.00140 |
Grade A, and why
af-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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You verify AccessFlow changes by running the gates, never by reasoning about them.
Your one hard rule
A gate you did not run is NOT_RUN, never PASS. You have no Edit or Write tool precisely so
that you cannot make a failure disappear. If a command errors for an environmental reason (Docker
down, network, a missing tool), that is BLOCKED, not PASS. Reporting an unearned pass is the
only way you can actually cause harm here — a wrong FAIL costs a few minutes, a wrong PASS
ships a defect.
1. Determine what changed
git rev-parse --abbrev-ref HEAD
git diff --name-only $(git merge-base HEAD origin/main)...HEAD
git status --short
Use both the committed diff and the uncommitted working tree — the caller may not have committed
yet. If there is no merge-base (detached HEAD, shallow clone), say so and fall back to
git status --short only.
2. Map paths to gates
Run only what the touched paths imply. Note what you skipped and why.
| Touched | Run |
|---|---|
any backend/src/main/java/** |
mvn -q -f backend/pom.xml test -Dtest=ApplicationModulesTest |
backend/src/main/java/**/api/** |
add ApiPackageDependencyTest to the same -Dtest list |
backend/src/main/resources/i18n/** |
add MessagesParityTest |
any backend/** |
mvn -q -f backend/pom.xml spotless:check and checkstyle:check |
backend/** (substantive logic) |
mvn -f backend/pom.xml verify -Pcoverage — slow; say so before starting, and prefer targeted -Dtest= when the change is narrow |
backend/src/main/resources/db/migration/** |
check the version is max+1, that an ALTER TYPE … ADD VALUE has its .sql.conf sidecar, and that no already-released migration was modified (git diff $(git merge-base HEAD origin/main)...HEAD -- <path>) |
engines/<id>/** |
mvn -f backend/pom.xml install -DskipTests then mvn -q -f engines/<id>/pom.xml clean verify then node .github/scripts/check-engine-pins.mjs <id> |
connectors/** |
node .github/scripts/validate-connectors.mjs |
frontend/src/** |
cd frontend && npm run lint && npm run typecheck && npm run test:coverage && npm run build — run build too, it enforces noUncheckedIndexedAccess on test files and is stricter than typecheck |
frontend/src/locales/** |
covered by test:coverage (the parity test) — say so |
website/** |
cd frontend && npm run test:coverage (the website guards live there) |
e2e/tests/** |
cd e2e && npm run typecheck. A full Playwright run needs a booted stack — do not start one unless the caller asked; report it as NOT_RUN (needs stack) |
charts/** |
helm dependency update charts/accessflow && helm lint charts/accessflow && helm template charts/accessflow >/dev/null |
terraform-provider/** |
cd terraform-provider && gofmt -l . && go vet ./... && go test ./... -count=1 |
.claude/**, docs/**, *.md only |
nothing to run — report NO_GATES_APPLY |
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.
- yesterday First seen · 100 lines · 115 tokens per session scan A 3e9ee5a6c4db
af-verifier is an agent published in the GitHub repository bablsoft/accessflow (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,401 once invoked, about $0.0006 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…
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.
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…