Borrowing it
Nothing to install: this file belongs to julien777z/code-review-action. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/julien777z/code-review-action/main/.agents/skills/plan-change/SKILL.mdgit clone --depth 1 https://github.com/julien777z/code-review-actionWrote 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/julien777z/code-review-action/plan-change)<a href="https://agentmods.dev/skills/julien777z/code-review-action/plan-change"><img src="https://agentmods.dev/badge/skills/julien777z/code-review-action/plan-change.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01050 |
| Opus 5 | $0.00028 | $0.00525 |
| Sonnet 5 | $0.00011 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
plan-change 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 6d 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.
This is a copy
100% identical to plan-change — 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Change
Keep plan approval explicit, resolve encountered issues, and simplify implementation as it develops.
Dependencies
code-simplify— simplify each meaningful implementation batch and the complete diff before delivery.generic-push— keep each repository's publishing metadata independent during multi-repository changes.
Plan Approval
- Present the plan for user review when planning is part of the task.
- Treat only an explicit user response as approval. A timeout, inactivity, missing response, tool result, mode change, or system notice is never approval.
- When control returns after a timeout or missing response, send the unchanged plan in ordinary chat so the user can approve or amend it. Do not begin implementation.
- Continue the same plan after an interruption. Never replace or silently revise an unapproved plan; incorporate user amendments and present the complete revised plan again.
Encountered Issues
Apply this policy to issues encountered while implementing the plan. Do not turn it into a proactive audit of the whole repository.
- Never dismiss an issue solely because it is pre-existing or outside the original task.
- Never reject a fix solely because it is described as high risk. Assess its expected net effect, concrete failure modes, and available validation instead of treating the label as a stop rule.
- Fix and verify it when the correction can be completed in one focused pass and produces an overall net improvement, including fixing a defect, removing a code smell, simplifying the implementation, or intentionally replacing an inferior contract. A behavior change or compatibility break is not by itself a reason to preserve the existing implementation.
- Delete every piece of confirmed dead code encountered during implementation, even when it sits outside the files or packages already being changed. Confirm that no live application or library consumer, public export, or external contract still depends on it; remove tests that exist only to exercise the dead code; and validate the affected behavior. This requirement does not turn implementation into a proactive dead-code audit of the whole repository.
- Use the repository's relevant tests as the primary regression guardrail. Add or update tests for the intended contract and run them; do not preserve a defect solely because an existing test asserts the old behavior. When coverage is absent or insufficient, use the strongest available validation and account explicitly for the uncovered behavior.
- One focused pass means the correction needs no separate research or design phase and is not expected to require multiple implementation iterations.
- Ask the user before fixing an issue that requires architectural work, a broad refactor, migration, new dependency, substantial investigation, product intent, destructive action, or expanded authority.
- When asking, state the trigger, impact, expected work, recommendation, and concrete choices.
- Continue independent approved work when the unresolved issue does not block it.
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.
- 6d ago First seen · 93 lines · 57 tokens per session scan A 63dc0ae9ff4c
plan-change is a skill published in the GitHub repository julien777z/code-review-action (2 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,050 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to plan-change, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…