meta-validate-context
Skill15 starsChanged 18 days agoApache-2.0View on GitHub
Use when auditing the freshness of `.claude/rules/subsystem-*.md` files against current codebase state, or when a subsystem has undergone significant change.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/research/hooks_vendor_reports/claude.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- code-docs-cleanupSkill
- docs-instrumentSkill
- docs-planSkill
- docs-reviewSkill
- hex-architectSkill
- hex-coreSkill
- hex-discussSkill
- hex-executeSkill
- hex-finalizeSkill
- hex-initSkill
- hex-loopSkill
- hex-planSkill
- hex-retroSkill
- hex-reviewSkill
- nox-reviewSkill
- bugfixSkill
- builderSkill
- changelogSkill
- code-checkSkill
- code-docs-cleanupSkill
- commitSkill
- docs-instrumentSkill
- docs-planSkill
- docs-reviewSkill
- docsSkill
- finalizeSkill
- hex-architectSkill
- hex-coreSkill
- hex-discussSkill
- hex-executeSkill
- hex-finalizeSkill
- hex-initSkill
- hex-loopSkill
- hex-planSkill
- hex-retroSkill
- hex-reviewSkill
- meta-maintain-configSkill
- nextSkill
- nox-reviewSkill
- qa-engineerSkill
- security-auditorSkill
- upstream-refreshSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Check .claude/rules/subsystem-*.md files match current codebase.
- Distinctive: line 70
Before major feature branches
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Validate Context Rules
Check .claude/rules/subsystem-*.md files match current codebase.
Workflow
For each subsystem-*.md rule file:
- Read the rule — Extract type names, module paths, function names, error variants
- Grep the codebase — Verify each reference exists
- Check for new additions — Find new public types/modules not in rule
- Report — List stale references + missing additions
Subsystem Rules to Check
| Rule | Key References to Verify |
subsystem-cli.md | CLI context struct, command enum variants, output trait |
subsystem-cli-api.md | Report data types, output trait conventions |
subsystem-cli-commands.md | Documented command surface vs implemented commands |
subsystem-file-structure.md | Storage layout, data-root constraints |
subsystem-tests.md | Fixture names in conftest.py, test file names, runner methods, helper params |
Subsystem rules are provisional placeholders while the implementation is
scaffolded — verify against current src/ as code lands.
Verification Commands
# Check if a type still exists
grep -r "pub struct TypeName" src/
grep -r "pub enum TypeName" src/
# Check if a module still exists
ls src/module_name/
# Check for new public types not in the rule
grep -rn "^pub struct\|^pub enum\|^pub trait" src/ | grep -v testOutput Format
## Context Validation Report
### subsystem-cli.md
- OK: [type] still present
- STALE: [type] — renamed to [new_name] or removed
- MISSING: [new_type] — not documented in rule
### subsystem-file-structure.md
...When to Run
- After big refactors
- Before major feature branches
- Part of
/code-checkaudits - Monthly
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.

