agentmods.dev

drift: Skill for Claude Code

.github/skills/guard-src-drift-output/SKILL.md

guard-src-drift-output is a skill for Claude Code from mick-gsk/drift. It costs 72 tokens per session (1,003 once invoked), scanned A, original, MIT.

A project-specific coding guide for the output-rendering code in src/drift/output. It explains where formatting belongs and flags a design problem when display code starts doing calculations or recommendation work.

In plain words
What is it for?
Changing how findings appear, adding an output format, editing the listed formatter files, or handling reported design drift in that module.
Why use it?
It helps prevent output code from becoming tangled with scoring, aggregation, and other application logic. That makes changes to reports and renderers easier to assess safely.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is mick-gsk/drift's own configuration. It tells Claude Code how to work on drift 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 drift configures →

Part of the drift plugin — 31 skills, 17 agents shipped together

not rated 15repo +1 1mo ago A scan 72 tokens original MIT
View source ↗ mick-gsk/drift mick-gsk.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to mick-gsk/drift. 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/mick-gsk/drift/main/.github/skills/guard-src-drift-output/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mick-gsk/drift

Made for: Claude Code.

Or install drift, the plugin that ships this one along with the rest of its 31 skills, 17 agents.

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 guard-src-drift-output

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/guard-src-drift-output/github.svg)](https://agentmods.dev/skills/mick-gsk/drift/guard-src-drift-output)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/guard-src-drift-output"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/guard-src-drift-output/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.

agentmods 80×15 button for guard-src-drift-output

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/guard-src-drift-output"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/guard-src-drift-output.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,003 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 $0.00072 $0.01003
Opus 5 $0.00036 $0.00502
Sonnet 5 $0.00014 $0.00201
Haiku 4.5 $0.00007 $0.00100

Measured 9d ago against content hash e7928714e52e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

guard-src-drift-output 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 9d 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.

.github/skills/guard-src-drift-output/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guard: src/drift/output

src/drift/output enthaelt 16 Formatter-Dateien: rich_output.py, json_output.py, markdown_report.py, llm_output.py, badge_svg.py, guided_output.py, grouping.py, u.a. Jede Datei verantwortet genau ein Ausgabeformat. EDS entsteht wenn Formatter anfangen zu berechnen was sie nur rendern sollten.

Konfidenz: 0.95 — das Output-Modul hat den schwersten EDS-Befund: komplexe Verschraenkung zwischen Formatierung, Aggregation und Empfehlungslogik.

When To Use

  • Du aenderst wie Findings angezeigt, formatiert oder gerendert werden
  • Du fuegest ein neues Ausgabeformat hinzu
  • Du aenderst rich_output.py, json_output.py, markdown_report.py oder guided_output.py
  • Drift meldet EDS fuer eine Datei in src/drift/output/

Warum dieses Modul kritisch ist

EDS tritt hier auf weil Formatter historisch begannen, eigene Aggregate zu berechnen:

  • guided_output.py kennt Scoring-Logik, die eigentlich in scoring/ liegt
  • markdown_report.py aggregiert Finding-Counts, die eigentlich in models/ stehen sollten
  • rich_output.py hat Farb-Logik UND Layout-Logik UND Conditional-Logik gemischt

Jede neue Berechnung in einem Formatter verstaerkt diese Verschraenkung.

Core Rules

  1. Formatter berechnen nicht — sie rendern — ein Formatter erhaelt ein RepoAnalysis- oder list[Finding]-Objekt und gibt formattierten Text/Dict/SVG zurueck. Keine eigene Score-Berechnung, kein eigenes Grouping-Erstellen.

  2. Gemeinsame Ausgabe-Logik gehoert in grouping.py — wenn zwei Formatter dieselbe Sortier- oder Gruppierungslogik brauchen, gehoert sie in grouping.py. Kein Copy-Paste zwischen Formattern.

  3. json_output.py ist Single Source of Truth fuer das JSON-Schema — das Schema in drift.output.schema.json muss mit dem tatsaechlichen Output von json_output.py uebereinstimmen. Aenderungen an einem erfordern Aenderungen am anderen.

  4. Neue Ausgabeformate als eigene Datei — kein neues Format als zusaetzliche Funktion in rich_output.py oder json_output.py. Eine neue Datei wie sarif_output.py oder csv_output.py ist der richtige Weg.

Read the full file on GitHub · 60 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. 9d ago First seen · 60 lines · 72 tokens per session scan A e7928714e52e

Subscribe to this mod's changes

guard-src-drift-output is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,003 once invoked, about $0.0004 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.

Debuggingai-generated-codearchitectureclicode-qualitycopilot
Related

Other skills, from other repositories

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

truecourse-fix

Fix TrueCourse violations that have suggested fixes.

truecourse-ai/truecourse · 13 tokens

truecourse-list

List TrueCourse violations found in this repository.

truecourse-ai/truecourse · 12 tokens

argot-refresh

Refresh Argot's committed fit snapshot safely — first diagnose why maintenance is recommended, re-audit corpus scope and structural path changes, review stale mutes and policy entries with the user, then fit locally, verify, and prepare the reviewed .argot/ update. Use when argot status, argot check, MCP, or CI…

get-tmonier/argot · 136 tokens

health

/health - Framework Health Diagnostics.

samibs/skillfoundry · 8 tokens

performance

You are the Performance Specialist, a rigorous engineer who identifies and eliminates performance bottlenecks. You measure everything, optimize systematically, and never guess.

samibs/skillfoundry · 5 tokens