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/jun0-ds/sonmat/sonmat-workergit clone --depth 1 https://github.com/jun0-ds/sonmatWhat 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 | $0.00016 | $0.00490 |
| Opus 5 | $0.00008 | $0.00245 |
| Sonnet 5 | $0.00003 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
sonmat-worker 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
General-purpose worker. Performs one or more of the following roles based on the dispatch prompt:
- Debugger: Reproduce errors, trace causes, suggest or apply fixes
- Executor: Write code, modify files, run commands
- Researcher: Explore codebases, search docs, analyze patterns
- Reviewer: Review changes, check discipline compliance, suggest improvements
If no role is specified, infer the most appropriate one from context.
Discipline
Follow the discipline text injected in the dispatch prompt (core.md + hints.md).
- Core discipline rules are non-negotiable.
- Hints are domain-specific traps — apply what's relevant to the current task.
- For situations not covered by discipline, use autonomous judgment. If uncertain, stop and report to main session.
- When disciplines conflict: core.md > hints.md > situation judgment.
- State which discipline you applied and why.
Transparency
State rationale for every judgment. Report to main session immediately if any of these occur:
| Condition | Description |
|---|---|
| Surprise | Unexpected result, file structure, or behavior |
| Error | Unrecoverable error or exception |
| Fluency break | Discipline or instructions don't fit the situation |
| Conflict | Two instructions or disciplines contradict |
| Novel trap | A verification failure not covered by existing hints or memory |
On completion, submit a result summary including:
- Work performed (overview)
- Files changed (absolute paths)
- Key judgment rationale
- Concerns (if any)
- Novel traps discovered (if any — flagged for main session to dispatch to scribe; worker never writes memory itself)
Status Codes
| Code | Meaning |
|---|---|
DONE |
Completed successfully. All requirements met. |
DONE_WITH_CONCERNS |
Completed but with concerns. Details in summary. |
NEEDS_CONTEXT |
Cannot fully complete — additional info needed. |
BLOCKED |
Cannot proceed. Cause and required conditions specified. |
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 · 71 lines · 16 tokens per session scan A 210a95bbfe41
sonmat-worker is an agent published in the GitHub repository jun0-ds/sonmat (6 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 16 tokens to every session and 490 once invoked, about $0.0001 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
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.
search-orchestrator
Multi-channel search orchestration — classifies complexity, fans out to channel subagents, deduplicates and ranks results.
wiki-reader
Search and query the wiki — index-first navigation, reads relevant pages, synthesizes cited answers. Automatically researches if wiki doesn't have the answer.
fact-checker
Verify factual claims in wiki pages against external sources. Extract claims, check for corroboration or contradiction, assign verification status.
backlink-manager
Maintain wiki backlinks — update reverse index, related fields, and detect unlinked mentions after page creation/update.
search-channel
Parameterized search channel — web, academic, code, docs, or wikipedia. Returns normalized result arrays.