faithful-capture

faithful-capture is a skill for Claude Code, Codex from friedbotstudio/baseline. It costs 111 tokens per session (2,162 once invoked), scanned A, original, Apache-2.0.

A set of rules for recording what someone actually said without adding guesses or unstated decisions.

In plain words
What is it for?
Use it when interviewing someone, clarifying requirements, writing an architecture decision record, extracting decisions, or saving user instructions as a lasting reference.
Why use it?
It helps prevent incorrect assumptions from entering conversations, requirements, decision records, or project notes.

Skill for Claude CodeCodex

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 skills/friedbotstudio/baseline/faithful-capture
Any agent
npx skills add friedbotstudio/baseline --skill faithful-capture
Clone the repo
git clone --depth 1 https://github.com/friedbotstudio/baseline

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 faithful-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/friedbotstudio/baseline/faithful-capture.svg)](https://agentmods.dev/skills/friedbotstudio/baseline/faithful-capture)
Your own site
<a href="https://agentmods.dev/skills/friedbotstudio/baseline/faithful-capture"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/faithful-capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,162 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 $0.00111 $0.02162
Opus 5 $0.00056 $0.01081
Sonnet 5 $0.00022 $0.00432
Haiku 4.5 $0.00011 $0.00216

Measured 5d ago against content hash 28e35326fd88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

faithful-capture 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 5d 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.

.claude/skills/faithful-capture/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

faithful-capture — record what was said, not what you inferred

You are capturing intent that lives in someone else's head. The output is either a turn of conversation or a durable record. In both cases the failure mode is identical: you fill space the speaker left unspecified, then treat your filling as theirs.

In conversation this costs the speaker a turn of reclaiming ground they never conceded. In a durable record it costs far more — a fabricated node gets cited later, defended by a future session as established fact, and outlives the context needed to detect it.

This skill is a discipline, not a phase. It runs inside whatever is doing the capturing.

Consumers

Caller What it is capturing Where it lands
Interview / design dialogue The speaker's intent, mid-formation Conversation, then a brief or spec
ADR authoring A fork that was taken, and why Decision node / ADR
Decision extraction from _pending Forks detected in prior conversation Curated decision record
Memory promotion A rule or lesson the user stated Canonical memory entry

The eight rules

Each rule names the tell that detects a violation and the repair. The tells are mechanical — apply them to your own draft before it ships.

R1 — Quote before you critique

Before evaluating any element, locate the speaker's actual words for it.

  • Tell: you are about to criticize something you cannot quote from what they wrote.
  • Repair: you have no target. Convert the criticism into a question, or delete it.

An unquotable critique is always self-critique wearing someone else's name. This is the parent rule; R2, R3 and R4 are the three ways it gets violated.

R2 — Illustration is not commitment

for example, like, e.g., etc, say, something such as mark an item as illustrative. Illustrations show the shape of a category. They are not proposals.

  • Tell: you are evaluating a list item that arrived under an example marker.
  • Repair: treat the category as proposed and the item as disposable. If the item matters, ask whether it was meant as a commitment.

Read the full file on GitHub · 192 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. 5d ago First seen · 192 lines · 111 tokens per session scan A 28e35326fd88

Subscribe to this mod's changes

faithful-capture is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 111 tokens to every session and 2,162 once invoked, about $0.0006 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.