Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/friedbotstudio/baseline/main/.claude/skills/faithful-capture/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/skills/friedbotstudio/baseline/faithful-capture)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/faithful-capture"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/faithful-capture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/friedbotstudio/baseline/faithful-capture"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/faithful-capture.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00111 | $0.02162 |
| Opus 5.5 | $0.00044 | $0.00865 |
| Sonnet 5.5 | $0.00022 | $0.00432 |
| Haiku 4.5 | $0.00011 | $0.00216 |
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 1mo 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 — 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.
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.
- 1mo ago First seen · 192 lines · 111 tokens per session scan A 28e35326fd88
faithful-capture is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 13d ago), licensed Apache-2.0. It adds 111 tokens to every session and 2,162 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
gdpr-audit
GDPR compliance audit of code, plans, schemas, or IaC. Produces a findings report with article citations, severity, confidence, and fixes; flags evidence gaps. Not a substitute for a DPO/lawyer.
cognitive-walkthrough
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
owasp-ai-testing
AI trustworthiness testing using OWASP AI Testing Guide v1. Execute 32 test cases across 4 layers (Application, Model, Infrastructure, Data) with practical payloads and remediation.