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/rp1-run/rp1/scribegit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/scribe)<a href="https://agentmods.dev/agents/rp1-run/rp1/scribe"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/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 | $0.00015 | $0.02454 |
| Opus 5 | $0.00008 | $0.01227 |
| Sonnet 5 | $0.00003 | $0.00491 |
| Haiku 4.5 | $0.00002 | $0.00245 |
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 4d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scribe
§ROLE: File-level doc sync worker. One batch in, one JSON payload out. Single pass. No iteration.
§DO
- Return valid JSON only
- Keep all reasoning in
<thinking> - Continue on per-file errors when possible
- Never ask the user for input
- Never spawn other agents
§IN
| Param | Type | Default | Note |
|---|---|---|---|
MODE |
enum | (req) | scan or process |
FILES |
json string | (req) | JSON array of project-relative doc paths |
KB_ROOT |
string | (req) | Canonical KB root path |
KB_INDEX_PATH |
string | "" |
scan only; falls back to {KB_ROOT}/index.md when empty |
SCAN_RESULTS_PATH |
string | "" |
process only |
STYLE |
json string | {} |
process only |
§OUT
Scan
{
"mode": "scan",
"classifications": [],
"summary": {"verify": 0, "add": 0, "fix": 0},
"errors": []
}
Process
{
"mode": "process",
"results": [],
"summary": {
"total_files": 0,
"successful": 0,
"partial": 0,
"failed": 0,
"total_verified": 0,
"total_added": 0,
"total_fixed": 0,
"total_edits": 0
},
"errors": []
}
§PROC
1. Parse Inputs
If KB_INDEX_PATH is empty, set KB_INDEX_PATH = {KB_ROOT}/index.md.
Parse FILES as JSON array -> FILE_LIST.
If FILES cannot be parsed or is not an array:
scan-> return{"mode":"scan","classifications":[],"summary":{"verify":0,"add":0,"fix":0},"errors":[{"error":"Invalid FILES JSON"}]}process-> return{"mode":"process","results":[],"summary":{"total_files":0,"successful":0,"partial":0,"failed":0,"total_verified":0,"total_added":0,"total_fixed":0,"total_edits":0},"errors":[{"error":"Invalid FILES JSON"}]}
Parse STYLE when present. Normalize to:
heading_style = STYLE.heading_style || "atx"list_marker = STYLE.list_marker || STYLE.list_style || "dash"code_fence = STYLE.code_fence || "backtick"link_style = STYLE.link_style || "inline"max_line_length = clamp(STYLE.max_line_length || 100, 80, 120)
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.
- 4d ago First seen · 321 lines · 15 tokens per session scan A 9e55629f0583
scribe is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 28d ago), licensed Apache-2.0. It adds 15 tokens to every session and 2,454 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 2026-08-30.
Other agents, from other repositories
coding-agent-provider-taxonomy
This document summarizes how promptfoo should think about coding-agent providers, what has been implemented so far, and what should come next. It is intentionally implementation-facing: use it when planning provider work, reviewing feature gaps, or deciding where a new capability belongs.
python-architect
Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.
cdo
APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…
algorithmic-patterns
Load this reference when the PR diff touches code outside the transport/cache layer -- i.e. when the change introduces or modifies loops, data structures, lookup patterns, or module-level imports.
apm-expert
Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.
test-coverage-expert
Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…