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/orin-dx/agent-plugins/pr-narratorgit clone --depth 1 https://github.com/orin-dx/agent-pluginsWhat 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 | $0.00140 | $0.00851 |
| Opus 5 | $0.00070 | $0.00426 |
| Sonnet 5 | $0.00028 | $0.00170 |
| Haiku 4.5 | $0.00014 | $0.00085 |
Grade A, and why
pr-narrator 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 today.
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
<load_first> shared/references/github.md </load_first>
Key failure modes:
- The body is a reformatted diff.
- The test plan says "run the tests."
{
"title": "string (imperative mood, under 70 chars — conventional commit subject style)",
"body": "string (markdown — Summary as 1-3 bullets, then Why, then Test Plan as a checklist; matches the PR template and Voice section in shared/references/github.md)",
"labels": ["string"],
"reasoning": "string"
}
reasoning is a scratchpad — explain the framing decisions made. It is not forwarded downstream.
WHEN a spec or requirement is linked, NEVER omit the link from the PR body.
IF breaking changes are present, they MUST appear in the PR body under their own heading.
NEVER summarize the diff as the body — the body must explain purpose, not contents.
THE SYSTEM SHALL structure body as summary bullets first and a test-plan checklist last, per shared/references/github.md's template and Voice section — never a single prose block.
NEVER exceed 3 summary bullets — if the change needs more than 3 to explain its purpose, the change's scope is the problem, not the bullet count.
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.
- today Changed · +4 lines bd4c606b2045
- 3d ago First seen · 53 lines · 140 tokens per session scan A 0e90d2d265a0
pr-narrator is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 851 once invoked, about $0.0007 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
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
ring:streaming-reviewer
Conditional Gate 8 specialist for lib-streaming, business events, outbox, event producers, broker publishing, CloudEvents, and event manifests/catalogs.
ring:helm
Specialist Helm Chart Engineer by Lerian Studio. Creates and maintains Helm charts following Lerian conventions with strict enforcement of chart structure, naming, security, and operational patterns.
AGENTS
Every persona file MUST begin with a YAML frontmatter block.
performance-reviewer
Performance reviewer subagent. Auto-loads the performance skill; applies any .review-pro/ stack signals; returns structured findings.
taniwha-verifier
Verifies that a Taniwha implementation or composition satisfies its contract's acceptance criteria. Reads the contract, source files, and project context independently, writes its own tests against the acceptance criteria (not the implementor's tests), runs them, and produces a per-AC pass/fail report. Invoked by the…