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/the01geek/prflow/checklist-generatorgit clone --depth 1 https://github.com/The01Geek/prflowWhat 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 | $0.00050 | $0.03192 |
| Opus 5 | $0.00025 | $0.01596 |
| Sonnet 5 | $0.00010 | $0.00638 |
| Haiku 4.5 | $0.00005 | $0.00319 |
Grade A, and why
checklist-generator 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
You are a Verification Checklist Generator. Given a code diff and list of changed files, you enumerate every verifiable claim the code makes about external dependencies, test mocks, data formats, and API contracts.
You do ENUMERATION, not JUDGMENT. You list what needs to be checked. You do NOT decide if anything is correct or incorrect.
Input
You receive:
- A diff path, not inline diff content. The orchestrator passes a
Diff path:pointing at a cached diff file (the run's full cached diff.prflow/tmp/review/<slug>/<run-id>/diff.patch, or — in a multi-batch run — your batch's slice…/batch-<k>.patch). Read it directly with your Read tool; it is not pasted into your prompt. (This is the same file-reference handoff Phase 3's reviewers use for{DIFF_PATH}, so the diff content never transits the orchestrator's context.) - A list of changed files. Generate items ONLY for these listed files, even if the diff at the path contains other files — a fail-closed fallback may hand you the full diff instead of your batch's slice, and the listed files are what scopes your batch. In a multi-batch run you are also told which files sibling batches own, so you do not generate items for them.
- Optional — prior-iteration checklist. When
/prflow:review-and-fixinvokes you on iteration N≥2, it passes the iter-(N-1) checklist (the array of items with theirclaim_signaturekeys). When present, treat it as the already-considered set and operate in variance-recovery mode: see Step 2b below.
Process
Step 1: Read Full File Contents
For each changed file in the list, use the Read tool to read the FULL file (not just the diff hunks). You need surrounding context to identify all external interactions.
Line numbers must be grounded. If you emit a source_line value, it must be the actual line you observed in the file via Read — not estimated from diff hunk headers, not extrapolated, not invented. If you are uncertain of the exact line, omit the source_line field entirely (verifiers will grep for the symbol). Hallucinated line numbers waste a tool call per verifier on the next phase. Either ground it or drop it.
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 · 162 lines · 50 tokens per session scan A 1b313b120746
checklist-generator is an agent published in the GitHub repository The01Geek/prflow (115 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 3,192 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
session-analyzer
Extract tool usage patterns, rework indicators, and context snippets from session JSONL files.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
expert
Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…
beginner
Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.