card-generation

card-generation is a skill for Claude Code, Codex from tmj-90/gaffer. It costs 79 tokens per session (738 once invoked), scanned A, original, Apache-2.0.

An internal writing process that creates short file summaries from a file’s imports, top-level names, and possibly a small beginning excerpt. These summaries help an agent decide which files to read.

In plain words
What is it for?
Use it to create retrieval cards describing a file’s main responsibility and role. The original file must still be opened before editing.
Why use it?
It speeds up codebase navigation without pretending the summary is a replacement for reading the actual file.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/tmj-90/gaffer/card-generation
Any agent
npx skills add tmj-90/gaffer --skill card-generation
Clone the repo
git clone --depth 1 https://github.com/tmj-90/gaffer

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 card-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/tmj-90/gaffer/card-generation.svg)](https://agentmods.dev/skills/tmj-90/gaffer/card-generation)
Your own site
<a href="https://agentmods.dev/skills/tmj-90/gaffer/card-generation"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/card-generation.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 738 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 5.1 $0.00079 $0.00738
Opus 5 $0.00039 $0.00369
Sonnet 5 $0.00016 $0.00148
Haiku 4.5 $0.00008 $0.00074

Measured 6d ago against content hash 0cd690e5d020, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

card-generation 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.

packages/memory/skills/card-generation/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write one file card

A card is a RETRIEVAL AID: it helps an agent pick WHAT TO READ. It is NEVER authoritative source — the reader MUST open the file before editing. Say this wherever a card is surfaced.

You get: a file's MECHANICAL STRUCTURE (imports, top-level symbol names) and maybe a small HEAD SNIPPET. Nothing else — no full file, no language server, no runtime. Produce: tldr, one role_primary, up to 4 role_tags.

tldr (the key field)

Answers: what is this file's JOB and why does it EXIST?

  • 1–2 sentences, ≤400 chars (hard cap 500 — stay clear).
  • Concrete: name what it OWNS + its KEY responsibility.
  • No filename/path restating. No vague verbs ("handles/manages/processes/deals with") without saying specifically what.
  • Purpose unclear from the data? State what it STRUCTURALLY IS (e.g. "Zod schemas for the card record") instead of guessing intent.

GOOD: "Express router for /api/cards CRUD — owns the HTTP layer for card create/ read/search/delete. Read to trace request handling." BAD: "Handles authentication" · "Utility functions" · "src/math.ts implementation" · "Exports various helpers for working with the API".

role_primary — pick exactly ONE (dominant role)

entrypoint (main/CLI/process start) · route (HTTP handlers/routers) · service (domain/business-logic orchestration) · data-model (interfaces/Zod/ type-only) · migration (DB schema migrations) · config (config/env loaders/ flags) · test · util (pure side-effect-free helpers) · client (HTTP clients/ SDK wrappers/connectors) · middleware (framework middleware/interceptors) · store (state/caches/registries) · view (UI components/templates/renderers) · script (one-shot scripts/CLI tools) · types (type/interface-only modules).

role_tags — 0–4 secondary concerns

Short, lowercase, specific. e.g. ["auth","jwt"], ["fts","sqlite"].

Never invent (hard rule)

NEVER name a symbol or behaviour not shown in that file's structure block. A deterministic validator checks symbols against the real exports — invented ones FAIL the card and poison retrieval. Unsure → omit; omission is safe, invention is not. In batched prompts, use ONLY the file's own block (never another file's).

Read the full file on GitHub · 66 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. 6d ago First seen · 66 lines · 79 tokens per session scan A 0cd690e5d020

Subscribe to this mod's changes

card-generation is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 79 tokens to every session and 738 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 2026-08-31.

Related

Other skills, from other repositories

bulwark-brainstorm

Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.

QBall-Inc/the-bulwark · 50 tokens

plan-creation

Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.

QBall-Inc/the-bulwark · 38 tokens

anthropic-validator

Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.

QBall-Inc/the-bulwark · 40 tokens

code-review

Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.

QBall-Inc/the-bulwark · 61 tokens

create-subagent

Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.

QBall-Inc/the-bulwark · 42 tokens

test-audit

Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.

QBall-Inc/the-bulwark · 0 tokens