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 feO2x/guided-coding --skill write-deviationsgit clone --depth 1 https://github.com/feO2x/guided-codingWrote 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/feo2x/guided-coding/write-deviations)<a href="https://agentmods.dev/skills/feo2x/guided-coding/write-deviations"><img src="https://agentmods.dev/badge/skills/feo2x/guided-coding/write-deviations/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/feo2x/guided-coding/write-deviations"><img src="https://agentmods.dev/badge/skills/feo2x/guided-coding/write-deviations.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 | $0.00034 | $0.00906 |
| Opus 5.5 | $0.00014 | $0.00362 |
| Sonnet 5.5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
write-deviations 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- guided-coding-write-deviations — 98% identical, 7 lines differ
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.
Write Plan Deviations
Your goal is to decide whether the completed implementation needs a Plan Deviations document and, if so, to write it into the ai-plans/ folder at the repository root. After writing, report the document path and stop.
A Plan Deviations document summarizes how the completed implementation differs from the original plan. Reading the initial plan together with this document should be enough to understand the complete work.
1. Inspect the Plans and the Implementation
Read all plans for the current ticket in ai-plans/, oldest first. Identify them by the <ticket-id> or <short-title> in their file names, or by the plans mentioned in the conversation. Ask the user if the set of plans is unclear.
Determine the implementation range. Use the PR/MR if there is one. Otherwise, use the merge base between the target branch and the implementation branch. Inspect the commits in that range, all committed, staged, and unstaged changes, and any relevant earlier history. Verify every document and source-file reference you rely on.
2. Decide Whether a Document Is Needed
Write a Plan Deviations document in either of these cases:
- Follow-Up Plans exist. Summarize the changes from the first plan so that the first plan and this document explain the complete work.
- The implementation materially changes or rejects an explicit plan decision. This applies to decisions about at least one Acceptance Criterion, a public contract or data model, an architectural or component boundary, a security or performance constraint, or another design decision future maintainers need to know about.
Routine choices the plans left open are not deviations. An Acceptance Criterion that is documented but not met remains incomplete; it does not count as a deviation unless an accepted Follow-Up Plan explicitly supersedes it.
If there is only one plan and no material deviations, report that conclusion to the user, create nothing, and stop.
3. Determine the File Name
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 Changed 9602d1181ac4
- 1mo ago First seen · 60 lines · 34 tokens per session scan A 06318e5f90f5
write-deviations is a skill published in the GitHub repository feO2x/guided-coding (6 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 906 once invoked, about $0.0001 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…