plan-critique
Skill13 starsChanged 2 months agoMITView on GitHub
Critique the user's plan from plan.md and write critique.md. Use when the user runs /plan-critique or asks for an adversarial review of an existing plan.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- 9thLevelSoftware/legiontheir own version, first seen May 5, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- 9thLevelSoftware/legion★ 76same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- plan-archiveSkill
- plan-createSkill
- plan-cycleSkill
- plan-executeSkill
- archiveSkill
- createSkill
- critiqueSkill
- cycleSkill
- executeSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
33 rules. About 0 are common, 12 are distinctive, and 21 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
21
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Read the working agreement at working-agreement.md before step 1 and follow it for the whole run.
- Distinctive: line 30
Check edge cases specific to the area the plan touches: concurrency, nulls, error paths, boundaries.
- Distinctive: line 32
Keep re-scanning the plan until two consecutive passes surface nothing new.
- Very specific: line 35
Do not edit project code or plan.md during this phase.
- Very specific: line 44
Read .copilot/plan-critique-config.json, get plansFolder path from settings.
- Very specific: line 49
If the variable is empty, use the literal value default instead.
- Very specific: line 52
Read the current session's plan from [plansFolder]/.sessions/[sessionId] if it exists.
- Very specific: line 55
If no plan folders exist: Respond with "No plans found.
- Very specific: line 57
If sessionPlan exists and matches a plan folder, auto-select it.
- Very specific: line 70
Update the session file [plansFolder]/.sessions/[sessionId] with the selected plan slug (create if needed).
- Very specific: line 71
Read the plan file at [plansFolder]/[selected-plan]/plan.md
- Very specific: line 73
If plan.md is empty: Respond with "Plan file is empty.
- Very specific: line 74
If no project instructions file exists: Respond with "Create a .github/copilot-instructions.md file in the root of your project."
- Very specific: line 78
Use Glob to check for TypeScript indicators: tsconfig.json, *.ts, or *.tsx files in the project
- Very specific: line 79
Use Glob to check for other language indicators, for example composer.json or *.php, go.mod, pyproject.toml, pom.xml
- Distinctive: line 83
If the probe succeeds, a language server is available.
- Distinctive: line 85
If the probe fails or no language server is running for the detected language, inform the user before continuing: "No language server …
- Distinctive: line 90
Do not block the critique.
- Very specific: line 92
Read the existing "Iteration: [number]" at [plansFolder]/[selected-plan]/critique.md (if it exists) and determine the current iteration …
- Very specific: line 94
If the plan references files that are in the [plansFolder]/[selected-plan]/ folder, review those as well and add them to the context of the …
- Distinctive: line 118
When suggesting a split, be specific about which sections should become their own plan.
- Very specific: line 119
Write the critique to [plansFolder]/[selected-plan]/critique.md.
- Very specific: line 120
When writing the critique, follow the original chapters from plan.md.
- Distinctive: line 123
Use the format in critique-format.md.
- Very specific: line 127
When critiquing, always analyze codebase structure (existing files, directories, patterns), the project instructions, the README.md file, …
- Very specific: line 130
When doing the writeup of the critique, in the "Description" area make use of the line numbers from plan.md and reference them so that the …
- Distinctive: line 132
Use code intelligence to verify the plan against the actual codebase.
- Very specific: line 134
Verify types exist: use the LSP go-to-definition operation.
- Very specific: line 136
Check method/function existence: use LSP go-to-definition.
- Distinctive: line 141
Verify file paths exist with Glob before referencing them in the critique
- Distinctive: line 142
Add the found issues/observations list in the beginning of the critique.md file as a Table of contents
- Distinctive: line 143
Always follow the chapters from plan.md as a structure for critique
- Distinctive: line 148
Only include current issues: The critique should reflect the current state of plan.md.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are performing an iterative review of the user's execution plan. Critique the plan, code, architecture, system design, and design patterns.
Fixed rules:
Read the working agreement at working-agreement.md before step 1 and follow it
for the whole run. If that path does not resolve, look for working-agreement.md in the project root, then in
.github/. If it cannot be found anywhere, tell the user it is missing and apply the rules listed below.
These rules bind this phase and override any step below that conflicts with them:
- Be adversarial. Try to refute each finding before you write it down, and report only what survives the attempt. A finding you could not refute is worth more than three you did not test.
- Grade confidence per finding. Report a finding as CONFIRMED only when you verified it against the codebase. Label everything else UNVERIFIED and state what you could not check and why.
- Prove every finding with evidence: a
file:linereference, a command output, or a failing test. Never assert a plausible but unverified conclusion, and never present a guess as a fact. - Cite
plan.mdline numbers only from the copy you read in this run. Re-readplan.mdbefore writing the critique and check that each line reference points at the text you describe. Merging a critique into the plan shifts every line below the merge point, so numbers carried over from an earlier iteration are wrong. - Check edge cases specific to the area the plan touches: concurrency, nulls, error paths, boundaries. A generic "find bugs" pass over the plan is not enough.
- Keep re-scanning the plan until two consecutive passes surface nothing new. Stop at that point, not before.
- Require the plan to state its affected files and its verification approach. When a chapter is missing either one, raise it as a finding, because unlisted files are where import and dependency breakage hides.
- Do not edit project code or
plan.mdduring this phase. This phase writescritique.mdonly. The user decides what moves into the plan. - Be brief. No filler, no preamble, no emojis, no em dashes, no bold or italic text.
In this skill, "project instructions" means the first of these files that exists in the project root:
.github/copilot-instructions.md, AGENTS.md, or CLAUDE.md.
To do this, follow these steps precisely:
- Read
.copilot/plan-critique-config.json, getplansFolderpath from settings. If that file does not exist, read.claude/plan-critique-config.jsoninstead. If neither file exists orplansFolderis not set or is an empty string: Respond with "No plans folder configured. Run/plan-createfirst to set up." - Get the Copilot CLI session id from the
COPILOT_AGENT_SESSION_IDenvironment variable. Read it withecho $COPILOT_AGENT_SESSION_IDon macOS or Linux, or$env:COPILOT_AGENT_SESSION_IDon Windows. If the variable is empty, use the literal valuedefaultinstead. Store this assessionId. - Clean up stale sessions: scan
[plansFolder]/.sessions/for files and delete every file that has not been modified in the last 7 days. This is non-blocking cleanup, never abort the run because of it. - Read the current session's plan from
[plansFolder]/.sessions/[sessionId]if it exists. Store assessionPlan. - Scan
[plansFolder]/for subdirectories (each subdirectory is a plan). Excludearchived/and.sessions/folders and any files, only list plan directories. If no plan folders exist: Respond with "No plans found. Create one with/plan-create". - Select the plan to critique:
- If
sessionPlanexists and matches a plan folder, auto-select it. Inform the user: "Using current session plan: [sessionPlan]" - Else if only one plan exists, auto-select it and inform user.
- Otherwise, ask the user to select a plan from the list.
Example:
Available plans: 1. add-user-authentication 2. refactor-database-layer 3. implement-caching Which plan would you like to critique? [1-3]
- If
- Update the session file
[plansFolder]/.sessions/[sessionId]with the selected plan slug (create if needed). - Read the plan file at
[plansFolder]/[selected-plan]/plan.md - Check for errors:
- If
plan.mdis empty: Respond with "Plan file is empty. Edit[plansFolder]/[selected-plan]/plan.md" - If no project instructions file exists: Respond with "Create a
.github/copilot-instructions.mdfile in the root of your project."
- If
- Detect project languages and verify language server availability. Code intelligence is the required tool
for code verification in this phase, so this check is mandatory:
- Use Glob to check for TypeScript indicators:
tsconfig.json,*.ts, or*.tsxfiles in the project - Use Glob to check for other language indicators, for example
composer.jsonor*.php,go.mod,pyproject.toml,pom.xml - Probe the language server: pick a source file referenced by the plan (or any project source file) and request go-to-definition or hover on a known symbol.
- If the probe succeeds, a language server is available. Use it for all code verification in this run, as described in the Notes below. Do not substitute Grep for checks the language server can answer.
- If the probe fails or no language server is running for the detected language, inform the user before
continuing:
"No language server detected for [language]. The critique will fall back to Grep, which is less
accurate. Configure a language server with the
/lspcommand, or use an LSP setup skill such as https://github.com/github/awesome-copilot/tree/main/skills/lsp-setup to install and configure one." - Do not block the critique. Proceed with the Grep fallback and record in the critique Summary that no language server was available, so the user knows symbol verification relied on Grep.
- Use Glob to check for TypeScript indicators:
- Read the existing "Iteration: [number]" at
[plansFolder]/[selected-plan]/critique.md(if it exists) and determine the current iteration number. If no critique exists, this is iteration 1. - If the plan references files that are in the
[plansFolder]/[selected-plan]/folder, review those as well and add them to the context of the critique. - Perform a thorough critique of the plan considering:
- Clarity: Are requirements specific and unambiguous?
- Completeness: Are all necessary steps included?
- Order: Are dependencies between steps correctly sequenced?
- Feasibility: Can each step be executed given the current codebase?
- Risk: Are there potential side effects or breaking changes?
- Standards: Does it comply with the project instructions?
- Scope: Is scope reasonable? Any unnecessary additions?
- Testability: How is success verified? Does each chapter name the test to write or the command to run?
- Affected files: Does each chapter list the files it creates, modifies or deletes, and are those paths real?
- Supporting materials: Are referenced files in the plan folder adequate?
Evaluate whether the plan can be split into independent tasks. If the plan contains multiple features or changes that can be executed separately, strongly recommend splitting it into separate plans. Why this matters:
- Reduces complexity during execution
- Limits the context window needed for each plan
- Makes critique iterations more focused and actionable
- Allows independent tasks to proceed without blocking each other
Example: A plan with "Add user authentication", "Refactor database layer", and "Add caching" should be split into three separate plans if these can be implemented independently.
When suggesting a split, be specific about which sections should become their own plan.
Write the critique to
[plansFolder]/[selected-plan]/critique.md. When writing the critique, follow the original chapters fromplan.md. The goal is to be able to easily override theplan.mdif the user chooses to mergecritique.mdwithplan.mdUse the format in critique-format.md.
Notes:
- When critiquing, always analyze codebase structure (existing files, directories, patterns), the project
instructions, the
README.mdfile, dependencies (package.json, requirements.txt, etc.), git state if relevant, whether referenced files/APIs actually exist, supporting files in the plan folder. - When doing the writeup of the critique, in the "Description" area make use of the line numbers from
plan.mdand reference them so that the user can easily find what text to replace or update. - Use code intelligence to verify the plan against the actual codebase. Always use the language server when
step 10 confirmed it is available; use Grep only as a fallback when step 10 found no language server:
- Verify types exist: use the LSP go-to-definition operation; fallback is Grep for
class,interface,type, orstructdefinitions - Check method/function existence: use LSP go-to-definition; fallback is Grep for
function/def/fndeclarations in the target file - Find usages/references: use LSP find-references; fallback is Grep for the symbol name across the codebase
- Review diagnostics: use the LSP hover and definition operations on files referenced in the plan to surface current errors and warnings
- Verify file paths exist with Glob before referencing them in the critique
- Verify types exist: use the LSP go-to-definition operation; fallback is Grep for
- Add the found issues/observations list in the beginning of the critique.md file as a Table of contents
- Always follow the chapters from plan.md as a structure for critique
- Be direct and constructive in feedback
- Suggest multiple solutions when appropriate
- Each critique iteration completely overwrites the previous critique.md file.
- Discard addressed issues: If an issue from the previous critique has been fixed in plan.md, do not include it.
- Only include current issues: The critique should reflect the current state of plan.md.
- New unrelated observations: If new issues appear that don't fit under existing
plan.mdchapters, add them as new chapters at the bottom of the critique - Increment iteration number: Always increment from the previous critique's iteration number
- Critique is the most demanding phase. Select a high capability model with the
/modelcommand before running it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

