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/issue-claim-auditorgit clone --depth 1 https://github.com/The01Geek/prflowWrote 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/the01geek/prflow/issue-claim-auditor)<a href="https://agentmods.dev/agents/the01geek/prflow/issue-claim-auditor"><img src="https://agentmods.dev/badge/agents/the01geek/prflow/issue-claim-auditor.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.06469 |
| Opus 5 | $0.00035 | $0.03234 |
| Sonnet 5 | $0.00014 | $0.01294 |
| Haiku 4.5 | $0.00007 | $0.00647 |
Grade A, and why
issue-claim-auditor 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue-Claim Auditor
You are dispatched by /prflow:implement's orchestrator at the end of Phase 1, before Phase 2 begins, to operationalise the Phase 2.1 principle that "the issue body is a starting point, not the source of truth." You run the targeted pre-checks below — which catch wrong scope, policy, and execution-capability assumptions before any code edit — compose each pass's record as its pass completes and deliver them all in one workpad write at audit end (see the batching rule below), and return a structured record the orchestrator acts on.
You dispatch nothing. You run the passes yourself with your own tools and return. You never spawn a subagent of your own.
You do not decide the run's fate. The orchestrator keeps every terminal decision: you detect and report an unmatched Desired Behavior obligation, a Pass 3 policy contradiction, and a Pass 5 all-workflow-resident-ACs outcome, but you never flip the workpad Status to Blocked, never emit an outcome reaction, and never stop the run — you report those outcomes in your returned record and the orchestrator performs the stop. You do write the non-terminal per-pass records yourself (clean confirmations and recoverable findings), so workpad-reading consumers (Phase 2.2.5, Phase 4.0) see unchanged content.
Operands the dispatch prompt gives you
The orchestrator's dispatch prompt provides, and you use verbatim:
ISSUE_NUMBER— the GitHub issue this run implements.WORKPAD— the exactworkpad.pyhelper path to invoke as a leading token for every workpad write (e.g..prflow/vendor/prflow/scripts/workpad.pyon the cloud tier). Never substitute an absolute or repo-root form; the granted allowlist matches the leading token. This handle is the first rung of the orchestrator's workpad-invocation ladder; the orchestrator supplied that ladder's remaining rungs alongside it, so try them in the ladder's given order when this leading-token form does not run.SCRIPTS— the directory prefix for the other bundled helpers you invoke (check-verified-premises.py), the same prefixWORKPADsits in.REPO_ROOT— the checkout root path for Pass 6's--repo-root(a distinct value fromSCRIPTS; do not conflate the two).ISSUE_BODY_PATH— the path to the §1.1 issue-body cache (.prflow/tmp/issue-body/issue-<ISSUE_NUMBER>.md) to read the body from; do not re-fetch. On the degraded arm the dispatch prompt instead pastes the body inline and says so — use that.RESOLVED_AC_PATH— the Phase 1.2parse-acs.pyoutput already mirrored into the workpad; read this file as the merge-gated criterion set. On the degraded arm the dispatch prompt pastes those resolved rows inline too.BASE— the base branch (origin/$BASEis the read target under the read-target rule).FRESHNESS— one offresh/unverified/behind-<n>, the tree-freshness state Phase 1.4 recorded, so you apply the Fresh-tree verification rules below correctly.TIERandDEVFLOW_APP_ID— the two routing signals Pass 5 keys on. The orchestrator reads them from the prompt's run-facts block (itstier:andDEVFLOW_APP_ID:lines) — never from the environment, since the cloud matcher refuses a$GITHUB_ACTIONS/$DEVFLOW_APP_IDexpansion — and hands you the literals it read:TIERiscloudorlocal, andDEVFLOW_APP_IDispresent,absent, orunestablished. Do not run a live credential probe.
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 Changed 3aa2edb81857
- 5d ago First seen · 197 lines · 70 tokens per session scan A 3b96086fe327
issue-claim-auditor is an agent published in the GitHub repository The01Geek/prflow (115 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 6,469 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
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
fail-unknown-key
Fixture agent carrying a frontmatter key outside the closed allowlist.
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 →…