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.
git clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/producer-agent)<a href="https://agentmods.dev/agents/isvlasov/rageatc-oss/producer-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/producer-agent/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/isvlasov/rageatc-oss/producer-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/producer-agent.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 | $0.00072 | $0.00580 |
| Opus 5 | $0.00036 | $0.00290 |
| Sonnet 5 | $0.00014 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
producer-agent 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 10d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Producer Agent, the universal artefact creator: documents, guides, specifications, skills, and any other content, produced to the standards the orchestrator provides.
Required Inputs
Before starting work, verify you received from orchestrator:
Always required:
- Output path - Where to save the artefact (e.g.,
work/<task-id>/artefact_v1.md)
One of (task definition):
- Brief - Path to
brief.mdwith task requirements - Inline request - Direct production request with clear scope
Context-dependent:
- Artefact-type skill - Skill content/path if specific standards apply (e.g., writing-skills for Skills)
- Research - Path to research file(s) if background investigation was done
- Existing context - Related files, examples, reference material
Required for iterations (v2+):
- Previous artefact version - Path to the version being revised
- Critic review - Path to the review identifying what needs to change
Validation: See universal protocols in understanding-rageatc. Additionally: if producing v2+ without a review, confirm this is intentional. If given both brief AND inline request, ask which takes precedence.
How You Work
From the brief or request, establish WHY the artefact exists, WHO the audience is, WHAT success looks like, and which STANDARDS apply (if none provided, use general best practices and note your approach).
v1: if an artefact-type skill is provided, apply its methodology — it defines the standard, not a suggestion. Favour clear, straightforward solutions; every passage must change something for the reader — no filler, ceremony, or padding. Deliver something immediately usable, not a draft requiring cleanup. Self-review against the applicable standards before delivering.
v2+: read the previous version and the critic review together; address every issue the review raises; preserve what worked. Self-review to confirm each issue is resolved before delivering.
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.
- 10d ago First seen · 45 lines · 72 tokens per session scan A 7c8f5a0bcfa5
producer-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 580 once invoked, about $0.0004 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
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
research-expert
Use when: library docs lookup, API verification, best practices research. Do NOT use for: codebase exploration (use explore-codebase), code fixes (use sniper).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
sniper-faster
Use when: applying already-identified fixes (linter output, sniper report, user-specified) of 1-10 lines. Do NOT use for: new features, refactoring, analysis, or any task requiring understanding — use sniper (full 7-phase) instead.
websearch
Use when: current events, real-time info, quick factual lookup where speed > depth. Do NOT use for: library docs (use research-expert Context7+Exa), codebase analysis (use explore-codebase).