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 skills add Hyperion-GPU/ProofFlow-v0.1 --skill proofflow-maintainergit clone --depth 1 https://github.com/Hyperion-GPU/ProofFlow-v0.1Wrote 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/skills/hyperion-gpu/proofflow-v0.1/proofflow-maintainer)<a href="https://agentmods.dev/skills/hyperion-gpu/proofflow-v0.1/proofflow-maintainer"><img src="https://agentmods.dev/badge/skills/hyperion-gpu/proofflow-v0.1/proofflow-maintainer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 37 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- low MCP Rug Pull · line 49 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
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 | $0.00050 | $0.02427 |
| Opus 5 | $0.00025 | $0.01213 |
| Sonnet 5 | $0.00010 | $0.00485 |
| Haiku 4.5 | $0.00005 | $0.00243 |
Grade A, and why
proofflow-maintainer 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 8d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProofFlow Maintainer
Use this skill when the user asks to use ProofFlow from Codex for repository maintenance, including:
- keep an Agent Work Ledger for complex code tasks,
- review the current diff with ProofFlow,
- create or export a Proof Packet for a PR,
- triage issue text into a ProofFlow Case,
- inspect or continue an existing ProofFlow Case,
- preserve evidence, decisions, actions, and policy gates while maintaining a repository.
Default to Agent Work Ledger for complex coding work. Use narrower workflows when the user's intent is clearly review-only, issue-intake-only, or packet export-only.
Operating Principles
- Keep the workflow local-first. The default ProofFlow backend is
http://127.0.0.1:8787. - Prefer ProofFlow MCP tools over ad hoc notes when recording Cases, Artifacts, Claims, Actions, Decisions, or Proof Packets.
- Treat the current AgentGuard review as provenance-first unless the returned Claims contain specific semantic findings. It proves what diff was reviewed and what evidence was captured; it does not by itself guarantee a complete semantic code review.
- Do not treat AI output as trusted unless it points to evidence. If evidence is missing, label the statement as an assumption.
- Do not run tests through ProofFlow unless the user explicitly asks and the backend is configured to allow test command execution.
- Do not merge PRs, close issues, or bypass policy gates unless the user explicitly asks and the repository workflow allows it.
Startup Check
Before running a ProofFlow workflow:
- Call
proofflow_health. - If the MCP server or backend is unavailable, tell the user to start the
backend and install
proofflow-mcpif needed:
pip install proofflow-mcp
cd backend
python -m uvicorn proofflow.main:app --port 8787
Choose The Workflow
- Use Agent Work Ledger for complex code tasks, multi-file changes, feature work, behavior changes, risky local actions, or any task that needs contract, algorithm decisions, cost budgets, snapshots, Evidence, Claims, done criteria evaluation, and packet export.
- Use AgentGuard review when the user only asks to review a current diff, PR, or branch changes.
- Use Issue Triage when the user provides issue text, logs, reproduction steps, or a bug report and wants it captured as a ProofFlow Case.
- Use Status / Proof Packet export when a Case already exists and the user wants a handoff artifact or review summary.
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.
- 8d ago First seen · 226 lines · 0 tokens per session scan A 0875443445d5
proofflow-maintainer is a skill published in the GitHub repository Hyperion-GPU/ProofFlow-v0.1 (49 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 2,427 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 skills, from other repositories
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
ln-51-opportunity-evaluator
Evaluates new product opportunities using demand, channels, competition, and economics. Not for committed-backlog or implementation planning.
specs
Use when a rough user story, bug report, feature idea, piece of feedback, or an implementation plan should be recorded as a GitHub issue — "file a ticket for this", "open an issue", "write this up for the backlog", "we should track this", "log this bug", "spec this out as a ticket so we can pick it up later" — i.e.…