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/README.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/readme)<a href="https://agentmods.dev/agents/bablsoft/accessflow/readme"><img src="https://agentmods.dev/badge/agents/bablsoft/accessflow/readme/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/readme"><img src="https://agentmods.dev/badge/agents/bablsoft/accessflow/readme.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 | $0.00000 | $0.02019 |
| Opus 5.5 | $0.00000 | $0.00808 |
| Sonnet 5.5 | $0.00000 | $0.00404 |
| Haiku 4.5 | $0.00000 | $0.00202 |
Grade A, and why
README 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
Seven read-only agents that explain a change and give it a second opinion. They are dispatched by
impl-gh-issue at step 5b (and
add-engine at step 13) before a change becomes a PR, and by
review-gh-pr against a PR that already exists: af-reviewer
and af-security-reviewer always run; the stack specialists run when their paths are touched;
af-verifier runs pre-PR always and post-PR only under --verify; af-pr-summarizer runs
whenever a human is about to read the result. All seven work standalone on any branch.
| Agent | Job | Tools |
|---|---|---|
af-pr-summarizer |
Explains what the change does: the one-paragraph what, the why, a per-area breakdown, the interface surface it moves (endpoints, migrations, enums, config, events), and where the risk concentrates. Describes; does not judge. | Read, Grep, Glob, Bash |
af-verifier |
Maps the touched paths onto the gates that actually apply and runs them. Reports PASS / FAIL / NOT_RUN / BLOCKED per gate. |
Read, Grep, Glob, Bash |
af-reviewer |
Cross-cutting reviewer: the fan-out completeness tables, the "same commit set" drift rules, website drift, backend↔frontend validation parity. Returns Blockers / Concerns / Nits with file:line evidence. |
Read, Grep, Glob, Bash |
af-security-reviewer |
Security specialist, whole repo but security lens only: proxy bypass, row security failing open, self-approval and tenant scoping, credential handling, the auth surface, SSRF, audit tamper-evidence, plugin supply chain. Same output format. | Read, Grep, Glob, Bash |
af-java-reviewer |
Backend/engine code specialist (backend/**, engines/**): CLAUDE.md backend rules + the backend/engine patterns/ checklists, incl. test parity. Same output format. |
Read, Grep, Glob, Bash |
af-frontend-reviewer |
Frontend/e2e code specialist (frontend/**, e2e/**): the frontend non-negotiables + the frontend/e2e patterns/ checklists, incl. e2e selector drift. Same output format. |
Read, Grep, Glob, Bash |
af-content-reviewer |
Docs/website content specialist (docs/**, website/**, README.md): claims checked against website/README.md's content-source map, readability, and the SEO surface the website tests do not cover. Same output format. |
Read, Grep, Glob, Bash |
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 Changed · +11 lines e28ffbe9e5d1
- 2mo ago First seen · 102 lines · 0 tokens per session scan A a4737dd589c3
README is an agent published in the GitHub repository bablsoft/accessflow (11 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,019 tokens. 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
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…
Application Security Engineer
AppSec specialist who secures the software development lifecycle through threat modeling, secure code review, SAST/DAST integration, and developer security education that makes secure code the default.
Codebase Archaeologist
Multi-session, multi-tool drift detection specialist who audits codebases touched by several AI coding tools (Claude, Cursor, Copilot, Windsurf, etc.) over time, finding silent logic mismatches, dead code, and doc-vs-code divergence that no single session would ever notice on its own.
Minimal Change Engineer
Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.
Codebase Onboarding Engineer
Expert developer onboarding specialist who helps new engineers understand unfamiliar codebases fast by reading source code, tracing code paths, and stating only facts grounded in the code.
Code Reviewer
Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.