trace-first-starter: Skill for Claude Code

.agents/skills/tfw-knowledge/SKILL.md

tfw-knowledge is a skill for Claude Code, Codex from saubakirov/trace-first-starter. It costs 48 tokens per session (290 once invoked), scanned A, original, MIT.

A workflow command that reviews unverified project facts and promotes only confirmed information into the project’s knowledge files.

In plain words
What is it for?
Use it to process fact candidates, update topic files and the knowledge index, maintain knowledge state, and report promoted, rejected, deferred, or unchanged facts.
Why use it?
It reduces the risk of treating guesses or observations as established project knowledge and keeps conflicting facts visible instead of silently resolving them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is saubakirov/trace-first-starter's own configuration. It tells Claude Code and Codex how to work on trace-first-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything trace-first-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saubakirov/trace-first-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saubakirov/trace-first-starter/master/.agents/skills/tfw-knowledge/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/saubakirov/trace-first-starter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tfw-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/saubakirov/trace-first-starter/tfw-knowledge.svg)](https://agentmods.dev/skills/saubakirov/trace-first-starter/tfw-knowledge)
Your own site
<a href="https://agentmods.dev/skills/saubakirov/trace-first-starter/tfw-knowledge"><img src="https://agentmods.dev/badge/skills/saubakirov/trace-first-starter/tfw-knowledge.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00048 $0.00290
Opus 5 $0.00024 $0.00145
Sonnet 5 $0.00010 $0.00058
Haiku 4.5 $0.00005 $0.00029

Measured 6d ago against content hash 5b8147f18855, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tfw-knowledge 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 6d 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/skills/tfw-knowledge/SKILL.md · 21 lines

What it actually says

/tfw-knowledge

This repository skill implements the /tfw-knowledge command.

Contract

  • Treat literal /tfw-knowledge input as a command. Also accept tfw-knowledge and matching natural-language requests.
  • Confirm the repository contains .tfw/.
  • Load AGENTS.md, .tfw/conventions.md, .tfw/glossary.md, .tfw/project_config.yaml, .tfw/knowledge_state.yaml, KNOWLEDGE.md, all knowledge/ topic files, task state across the configured containers, and candidate-bearing artifacts in that order.
  • Read .tfw/workflows/knowledge.md completely before consolidation; it is the canonical workflow.
  • Enforce the Coordinator role lock: permit knowledge/, KNOWLEDGE.md §4, knowledge state, and processed markers; forbid code and substantive edits to source artifacts.
  • Treat every Fact Candidate as unverified until the workflow verifies it. Never invent facts or resolve contradictions without the user.
  • Follow every WAIT gate and stop exactly where the workflow requires.

Report promoted, rejected, deferred, and unchanged facts with their sources.

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. 6d ago First seen · 21 lines · 48 tokens per session scan A 5b8147f18855

Subscribe to this mod's changes

tfw-knowledge is a skill published in the GitHub repository saubakirov/trace-first-starter (29 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 290 once invoked, about $0.0002 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.