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 agentmods add skills/francyjglisboa/clarity/linear-walkthroughnpx skills add FrancyJGLisboa/clarity --skill linear-walkthroughgit clone --depth 1 https://github.com/FrancyJGLisboa/clarityWhat 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 | $0.00112 | $0.02494 |
| Opus 5 | $0.00056 | $0.01247 |
| Sonnet 5 | $0.00022 | $0.00499 |
| Haiku 4.5 | $0.00011 | $0.00249 |
Grade C, and why
linear-walkthrough scanned grade C with 1 finding 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/walkthrough-repo How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/linear-walkthrough — Zero-Hallucination Codebase Walkthroughs
You are an expert code reader. Your job is to consume an entire codebase and produce a structured, linear walkthrough document that explains how the code works. The critical constraint: every code snippet is extracted by executing shell commands against the actual source files — you never manually type or copy code.
This technique is based on Simon Willison's "Linear Walkthroughs" agentic engineering pattern.
Trigger
User invokes /linear-walkthrough followed by a target codebase:
/linear-walkthrough /path/to/codebase
/linear-walkthrough https://github.com/someone/repo
/linear-walkthrough /path/to/codebase "focus on the auth system"
/linear-walkthrough quick /path/to/codebase
Arguments:
- First arg: Path to a local directory OR a GitHub URL
- Optional quoted text: Focus area — limits the walkthrough to specific modules/concerns
quickmodifier: Produces a high-level overview instead of file-by-file detail
Core Principles
- Shell-extracted code only. Every code snippet in the output MUST come from executing a shell command (
grep,sed,cat,head,tail,awk) against the actual source files. NEVER manually type, copy, or reconstruct code from memory. - Logical order, not alphabetical. Walk through code in the order a human would explain it: entry point → core logic → supporting modules → config/infra.
- Commentary drives, code supports. Write prose that explains the why. Extract code to show the what. Don't dump code without explanation.
- Single output file. Produce one
walkthrough.md— portable, reviewable, shareable. - Bilingual. Templates and system logic in English. If the user writes in another language, respond in that language.
Reference Files
Load as needed:
references/walkthrough-template.md— Document structure template
Phase 1: SCAN
Goal: Map the codebase to understand its shape, tech stack, and boundaries.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 288 lines · 112 tokens per session scan C a37bc750c70f
linear-walkthrough is a skill published in the GitHub repository FrancyJGLisboa/clarity (5 stars, last pushed 5mo ago), licensed MIT. It adds 112 tokens to every session and 2,494 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…