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.
npx skills add tmj-90/gaffer --skill code-tourgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/code-tour)<a href="https://agentmods.dev/skills/tmj-90/gaffer/code-tour"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/code-tour/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/tmj-90/gaffer/code-tour"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/code-tour.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 | $0.00102 | $0.01315 |
| Opus 5.5 | $0.00041 | $0.00526 |
| Sonnet 5.5 | $0.00020 | $0.00263 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
code-tour 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 20d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create persona-targeted, file-anchored code tours
A tour is a guided explanation (Diátaxis "explanation", anchored in code): a story for one reader about what matters, why, and where to go next. Every anchor must resolve against the current tree, and the tour must stay correct as the code moves.
Persona and depth
| Request mentions | Persona | Depth |
|---|---|---|
| a PR / diff | pr-reviewer | standard, only files the diff touches plus their callers |
| "why did X break", RCA | rca-investigator | standard, along the failing path |
| onboarding, new joiner, contributor guide, or nothing | new-joiner | standard |
| quick tour | vibecoder | quick |
| architecture | architect | deep |
| security, auth | security-reviewer | standard, trust boundaries and input handling |
Quick: 5–8 steps, 1–2 sentences each. Standard: 10–20 steps, 3–5 sentences. Deep: 20–40 steps including invariants, failure modes and design rationale. A repo with fewer than 5 source files gets a quick tour regardless.
Tour file format (CodeTour schema)
{
"$schema": "https://aka.ms/codetour-schema",
"title": "Request lifecycle — new joiner",
"description": "How an HTTP request becomes a database write, for someone new to the repo.",
"ref": "<commit sha the tour was verified against>",
"steps": [
{ "directory": "src", "description": "Everything that ships lives under src/ ..." },
{ "file": "src/server.ts", "pattern": "^export function main\\(", "title": "Entry point",
"description": "Execution starts here. `main()` wires config, the router and the DB pool. Next: the router." }
]
}
Required: top-level title and steps; each step needs description. Anchor a step with
file + line (1-based) or, preferably for code that will change, file + pattern (a
regex matched against line content — survives line shifts). directory steps introduce a
folder; a step with only description is a narrative interlude. Tours live in
.tours/<kebab-name>.tour.
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.
- 20d ago Changed · +8 lines 85c8af99b904
- 1mo ago First seen · 91 lines · 102 tokens per session scan A 74fb90ee22d6
code-tour is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,315 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 2026-08-31.
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.
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.
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.
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.
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.
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.