guided-coding-write-deviations

A skill for deciding whether completed guided coding work needs a plan-deviations document, then writing that document when the work materially changed its plan.

In plain words
What is it for?
Use it after implementation to compare plans with commits and changes, verify references, and document altered architecture, contracts, data models, security, or performance decisions.
Why use it?
It records important departures from the original design so future maintainers can understand what changed and why.

Skill for Claude CodeCodex

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/feo2x/guided-coding/guided-coding-write-deviations
Any agent
npx skills add feO2x/guided-coding --skill guided-coding-write-deviations
Clone the repo
git clone --depth 1 https://github.com/feO2x/guided-coding

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 621 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 98% copy Near-identical to another mod 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 $0.00037 $0.00621
Opus 5 $0.00018 $0.00311
Sonnet 5 $0.00007 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured yesterday against content hash a6eb3a61fa1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guided-coding-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 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.

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.

Origin

This is a copy

98% identical to write-deviations — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/guided-coding-write-deviations/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Plan Deviations

Inspect

  • Read all plans for the current work, oldest first.
  • Determine the implementation range from its PR/MR, or the target branch's merge base with the implementation branch.
  • Inspect its commits, all committed/staged/unstaged changes, and relevant earlier history. Verify every document and source-file reference.

Decide

Create the Plan Deviation Document if:

  • Follow-up plans exist: summarize changes from the first plan so it and this document explain the complete work.
  • The implementation materially changes or rejects an explicit plan decision about an acceptance outcome; public contract or data model; architectural or component boundary; security or performance constraint; or another design decision future maintainers need.

Exclude routine choices the plans left open. A documented but unmet acceptance criterion remains incomplete unless an accepted follow-up plan explicitly supersedes it.

Otherwise, with one plan and no material deviations, report that conclusion and create nothing.

Write

Use YYYY-MM-DD-HHMM-<issue-id>-plan-deviations.md; without a tracker issue, use YYYY-MM-DD-HHMM-<topic>-plan-deviations.md. Get UTC from the shell, never the conversation: date -u +%F-%H%M, or PowerShell (Get-Date).ToUniversalTime().ToString("yyyy-MM-dd-HHmm"). Normalize issue identifiers like the related plans. Resolve the full unused path. If any plan or Plan Deviations document already uses it, report the collision and stop; never overwrite or reuse.

Write:

  1. # <issue-id or topic> Plan Deviations.
  2. An opening paragraph naming every compared plan by exact filename and the implementation branch, and identifying unimplemented plans.
  3. ## Summary: what held up and how many material decisions changed.
  4. ## Changes Across Follow-Up Plans, when applicable: one numbered ### per superseded decision with Original decision, Superseded by (exact filename and replacement), Why, and Final outcome.
  5. ## Deviations From the Accepted Plans, when applicable: one numbered ### per material implementation deviation with Plan decision (exact filename and decision), Implemented, Why (required), and Impact (trade-offs, consequences, or deferred work; omit only if none).

Read the full file on GitHub · 59 lines

Files

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.

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. yesterday First seen · 59 lines · 37 tokens per session scan A a6eb3a61fa1a

Subscribe to this mod's changes

guided-coding-write-deviations is a skill published in the GitHub repository feO2x/guided-coding (6 stars, last pushed 18d ago), licensed MIT. It adds 37 tokens to every session and 621 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to write-deviations, differing in 7 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens