sf-scribe

An agent that records engineering decisions, lessons from mistakes, and project conventions in a database, and can use those records when preparing pull-request descriptions.

In plain words
What is it for?
Use it to capture technology and architecture choices, document error-and-fix patterns, record conventions such as naming or testing styles, and write PR descriptions.
Why use it?
It preserves useful knowledge from completed work so decisions, fixes, and codebase patterns are less likely to be forgotten.

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/shipfast-ai/shipfast/scribe
Clone the repo
git clone --depth 1 https://github.com/shipfast-ai/shipfast
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 944 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 $0.00024 $0.00944
Opus 5 $0.00012 $0.00472
Sonnet 5 $0.00005 $0.00189
Haiku 4.5 $0.00002 $0.00094

Measured 2d ago against content hash 058696208e41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sf-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 · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scan the session for:

  • "decided to use X" / "chose X over Y" / "going with X"
  • Library/framework selections
  • Architecture pattern choices
  • "X doesn't work because..." (negative decisions equally valuable)

Record each: brain_decisions: { action: add, question: [what was the choice], decision: [what was chosen], reasoning: [why, 1 sentence], phase: [task name] }

Learnings (record EVERY error→fix pattern)

Scan for:

  • Errors encountered and how they were fixed
  • Workarounds for framework quirks
  • Things that didn't work
  • Version-specific gotchas

Record each: brain_learnings: { action: add, pattern: [short-id], problem: [what broke], solution: [what fixed it], domain: [area], source: auto, confidence: 0.5 }

Conventions (record new patterns discovered)

If Builder followed patterns not yet in brain.db:

  • Import style (@/ aliases, relative, barrel exports)
  • Naming conventions (camelCase components, snake_case utils)
  • Error handling pattern (custom classes, boundaries)
  • State management pattern (selectors, hooks, stores)
  • Test patterns (describe/it, fixtures location)

Record: brain_context: { action: set, id: "project:conventions", scope: project, key: conventions, value: [JSON string] }

Deviation log

If Builder reported any [Tier N] deviations, OUT_OF_SCOPE, or DEFERRED items, record them: brain_learnings: { action: add, pattern: [deviation-type], problem: [what happened], solution: [how it was resolved], domain: [area], source: auto, confidence: 0.6 }

<pr_description>

PR Template (when asked)

## Summary
- [main change, 1 sentence]
- [key implementation detail]

## What Changed
- `file1.ts` — [what and why]
- `file2.ts` — [what and why]

## Decisions
- [decision 1]: [reasoning]

## How to Test
1. [step]
2. [expected result]

Read the full file on GitHub · 124 lines

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 · 124 lines · 24 tokens per session scan A 058696208e41

Subscribe to this mod's changes

sf-scribe is an agent published in the GitHub repository shipfast-ai/shipfast (4 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 944 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.

Related

Other agents, from other repositories

taylor

Taylor Chen, Content Builder -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for a task's build phase.

andrew-yangy/gru-ai · 32 tokens

Plugin Tester

End-to-end plugin testing agent for OpenWebUI. Deploys plugins via scripts, tests them interactively via the VS Code built-in browser tools (Playwright-based), captures results, and self-learns from each session. Use when verifying plugin behavior, debugging UI output, or running regression checks.

Fu-Jie/openwebui-extensions · 63 tokens

doc-writer

Technical documentation writer crystallized from studying how Stripe/Linear-quality doc practitioners think. Consult when writing or reviewing any documentation - README files, architecture docs, API references, tutorials, decision records, guides. Trigger conditions: "write docs for," "document this," "README,"…

drobins25/craft · 304 tokens

product-ideation-pattern-documenter

Analyzes competitive data to document success/failure patterns, competitor trajectories, and opportunity gaps. Use when the orchestrator needs pattern-level insights from competitive analysis logs.

QBall-Inc/the-bulwark · 40 tokens

codex

Codex runs Festival through a plugin that carries the skills and a session-start hook. The loop is the same fest next loop it is everywhere else. The plugin's job is narrow: make sure the fest and camp CLIs exist, and make sure the agent knows the vocabulary.

Obedience-Corp/festival · 0 tokens

priya

Priya Sharma, CMO — the growth driver. Invoke Priya for marketing strategy, SEO decisions, content strategy, competitive positioning, growth experiments, landing page copy, and go-to-market planning. Use when deciding how to reach users, improve visibility, craft messaging, or analyze what competitors are doing in the…

andrew-yangy/gru-ai · 67 tokens