deviate

An execution procedure for formally recording a change to an approved implementation plan. It pauses work, gets human approval, and stores the change as an append-only record, meaning earlier decisions are not silently rewritten.

In plain words
What is it for?
Use it during assign-to-workforce runs when execution no longer matches the confirmed plan and the deviation must be approved and recorded before continuing.
Why use it?
Real implementation can reveal wrong dependencies or changed acceptance criteria. This prevents the work from drifting away from the agreed plan without anyone noticing or approving the change.

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/agentculture/learn-cli/deviate
Any agent
npx skills add agentculture/learn-cli --skill deviate
Clone the repo
git clone --depth 1 https://github.com/agentculture/learn-cli

Made for: Claude Code, Codex.

Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% 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 $0.00167 $0.02398
Opus 5 $0.00084 $0.01199
Sonnet 5 $0.00033 $0.00480
Haiku 4.5 $0.00017 $0.00240

Measured yesterday against content hash 083e1ab1b6cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deviate 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

100% identical to deviate — 0 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.

.claude/skills/deviate/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deviate — record an approved mid-run departure from the confirmed plan

The skill is named deviate; it is the execution-time leg of the devague method — the sixth leg, sitting between the two execution skills:

scope -> think -> spec-to-plan -> assign-to-workforce -> deviate -> summarize-delivery

Where /assign-to-workforce fans out a converged plan's waves and /summarize-delivery closes the loop afterward, /deviate runs during the fan-out, at the exact moment reality stops matching the plan the human approved at gate 2 (the implementation split plan). It is not a new standing gate — it is the human owner of gate 2 amending the approved split mid-flight, scoped to the one deviation in front of them.

The plan the user confirmed is a contract. Task agents hit constraints, discover a dependency was wrong, or find the acceptance criteria no longer make sense once code is in front of them. Until this skill existed, that reality either silently reshaped what got built (undocumented drift) or the run stalled with no recorded path forward. /deviate is that path: the departure is named, approved, and recorded before anyone keeps building against it.

The method

  1. STOP the run. The moment a task agent (or the main agent) discovers the confirmed plan no longer matches what needs to happen, halt — do not keep implementing against the stale contract and do not let the fan-out continue past this task.
  2. Present what, why, and what it affects. Lay out, for the human:
    • what is diverging — the specific change from the confirmed task(s);
    • why — the constraint or discovery that forced it;
    • what it affects — the plan item ref(s) involved (--task), any other task ids or coverage targets it touches (--affects), and which acceptance criteria are no longer accurate.
  3. Get explicit human approval. This is the one non-negotiable step. A deviation is not real until a human says yes to this specific departure — not a standing blanket permission, not an inference from silence.
  4. Record it via devague deviate. Once approved, record the deviation as a first-class ledger entry (never edit the plan itself — the plan stays the untouched historical contract; see devague/delivery.py). An --origin llm record lands proposed and still needs the user's --confirm — recording is not the same as approval landing as final.
  5. Adjust the affected task briefs. Update the working instructions the task agent(s) are building against so they reflect the approved departure, not the stale plan text.
  6. Resume. Only after the record exists (and, for an llm-origin record, only after it is confirmed) does the fan-out continue.

Read the full file on GitHub · 177 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. yesterday First seen · 177 lines · 167 tokens per session scan A 083e1ab1b6cd

Subscribe to this mod's changes

deviate is a skill published in the GitHub repository agentculture/learn-cli (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 167 tokens to every session and 2,398 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deviate, differing in 0 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 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

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