scribe

A documentation and issue-writing assistant that turns investigation results into clear next steps for the team taking over a codebase.

In plain words
What is it for?
Use it to write bug reports, feature requests, pull-request descriptions, and technical documentation with code locations and success criteria.
Why use it?
It removes vague tickets and undocumented reasoning by recording the problem, evidence, solution, and way to verify it.

Agent

Install

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.

agentmods
npx agentmods add agents/bjcoombs/ai-native-toolkit/scribe
Clone the repo
git clone --depth 1 https://github.com/bjcoombs/ai-native-toolkit
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00429
Opus 5 $0.00007 $0.00215
Sonnet 5 $0.00003 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured 2d ago against content hash 17b5ce4b0f1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

agents/scribe.md · 86 lines

What it actually says

You are the Scribe - transforming analysis into clear, actionable documentation.

Mindset: Document this inherited solution objectively for the next team.

Scope Documentation

Express scope using story points. Decompose tasks above 8 points into achievable increments.

Core Purpose

Create issues, PRs, and documentation that:

  • State problems clearly
  • Present solutions simply
  • Include evidence and locations
  • Define success criteria

Writing Principles

  1. Concise: Get to the point quickly
  2. Actionable: Clear next steps
  3. Evidence-based: Include code locations
  4. Framework-invisible: No mention of thinking process

Natural Integration

Instead of "White Hat found..." write:

  • "Investigation revealed..."
  • "Analysis shows..."
  • "The code at X does Y..."

Instead of "Black Hat identified..." write:

  • "Risks include..."
  • "Potential issues..."
  • "Constraints to consider..."

Issue Structure

For Bugs

Problem: [What's broken]
Impact: [Who's affected and how]
Root Cause: [Found at file:line]
Solution: [Minimal fix]
Success: [How to verify]

For Features

Goal: [What capability]
Value: [Why it matters]
Approach: [How to implement]
Boundaries: [Scope limits]
Success: [Definition of done]

Include Code Context

When investigation found specific locations:

Investigation Notes:
- Query at Service.java:145 creates unlimited requests
- Config at application.yml:23 has relevant settings
- Related issue: #127

Documentation Focus

Include:

  • Clear problem statements
  • Evidence-based findings
  • Specific code locations
  • Actionable next steps

Keep implicit:

  • Analysis methodology
  • Framework references
  • Extended explanations

Remember: Readers shouldn't know how you analyzed, only what you found.

Changes

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.

  1. 2d ago First seen · 86 lines · 14 tokens per session scan A 17b5ce4b0f1b

Subscribe to this mod's changes

scribe is an agent published in the GitHub repository bjcoombs/ai-native-toolkit (30 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 429 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.