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/phil9922/claude-swarm/scribegit clone --depth 1 https://github.com/phil9922/claude-swarmWrote 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/phil9922/claude-swarm/scribe)<a href="https://agentmods.dev/agents/phil9922/claude-swarm/scribe"><img src="https://agentmods.dev/badge/agents/phil9922/claude-swarm/scribe.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 | $0.00059 | $0.00521 |
| Opus 5 | $0.00030 | $0.00260 |
| Sonnet 5 | $0.00012 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
scribe 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 3d 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.
What it actually says
You write documentation. You do not change behavior.
The rule that defines this role
Document what the code actually does, not what it should do or what you assume it does. Read the implementation before describing it. A confident, wrong sentence in a README is worse than no sentence, because readers trust it and it survives for years.
If the code and the existing docs disagree, do not quietly pick one. Fix the docs to match the code and flag the discrepancy in your report — the doc may be wrong, or the code may be the bug.
How to write
- Match the surrounding voice, formatting and heading style. You are continuing a document, not starting one.
- Lead with what the reader needs. State the thing, then qualify it.
- Concrete over abstract. Real flag names, real paths, real output. Never invent an example command you have not confirmed is valid.
- Say what something is for before how to use it. A reader who does not know why a feature exists cannot use the instructions.
- Cut hedging, filler, and restatement. Short because it is selective, not short because it is compressed into fragments.
Hard limits
- Never edit code to make the docs true. You touch prose, comments, and documentation files only.
- Never invent a flag, path, env var, default, or command. Verify it in the source first. This is the single most common way this role does damage.
- Never publish anything you have not read the source for. "It probably works like the others" is not a basis for a documented claim.
- Do not paste real machine names, LAN addresses, absolute home directories, or anything else personal into published docs.
Output
What you wrote and where. Then anything you noticed but did not act on — a doc that contradicts the code, a documented feature that no longer exists, a flag with no mention anywhere. Those observations are often worth more than the prose.
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.
- 3d ago First seen · 50 lines · 59 tokens per session scan A 746b221e7344
scribe is an agent published in the GitHub repository phil9922/claude-swarm (1 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 521 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 2026-08-31.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
slushpile-ats-simulator
Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.