dependency-grounding-auditor
Skill0 starsChanged 19 days agoMITView on GitHub
Verify proposed packages, versions, imports, and upgrade claims against project state and authoritative package metadata. Use before adding or changing a dependency.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- completion-claims-auditorSkill
- existing-work-preservationSkill
- mcp-reliability-auditorSkill
- multi-agent-integration-reviewerSkill
- project-context-recoverySkill
- requirement-traceability-auditorSkill
- scope-drift-guardSkill
- architecture-complexity-auditorSkill
- dependency-cycle-auditorSkill
- database-schema-reviewerSkill
- data-consistency-auditorSkill
- migration-safety-reviewerSkill
- loop-breakerSkill
- reproduction-builderSkill
- root-cause-debuggerSkill
- ci-failure-investigatorSkill
- cross-platform-readiness-auditorSkill
- environment-config-auditorSkill
- environment-parity-auditorSkill
- production-readiness-auditorSkill
- documentation-accuracy-auditorSkill
- token-efficient-workflowSkill
- accessibility-auditorSkill
- dead-feature-detectorSkill
- responsive-design-auditorSkill
- ux-state-completeness-auditorSkill
- release-verification-agentSkill
- agent-tool-trust-auditorSkill
- authentication-security-auditorSkill
- authorization-boundary-auditorSkill
- dependency-vulnerability-auditorSkill
- injection-risk-auditorSkill
- input-validation-auditorSkill
- secret-leakage-detectorSkill
- security-misconfiguration-auditorSkill
- api-contract-auditorSkill
- integration-reality-checkerSkill
- missing-test-detectorSkill
- regression-detectorSkill
- test-quality-auditorSkill
- ui-flow-verifierSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 10 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
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
- could be automatic: a setting could enforce it
- Distinctive: line 16
No dependency change is proposed and the task can be completed with existing project capabilities.
- Distinctive: line 20
Read applicable repository instructions before edits.
- Distinctive: line 32
Check whether the needed capability already exists in direct or transitive dependencies or the standard library.
- Distinctive: line 33
Verify the package name and import/module mapping using the local environment, lockfile, registry, or official docs.
- Distinctive: line 34
Verify the proposed version exists and supports the project's runtime/toolchain constraints.
- Distinctive: line 35
Check maintenance, license, security/advisory status, and whether the package is actually necessary for the task.
- Distinctive: line 36
Prefer pinned/locked reproducible changes consistent with the repository's package manager.
- Very specific: line 38
Run import/build/tests that prove the dependency is usable.
- Distinctive: line 46
Never execute an unreviewed install script outside the package manager or commit registry credentials.
- Distinctive: line 50
Every added name/version is grounded in an observed local or authoritative source.
- Distinctive: line 63
If registry/network access is unavailable, do not invent a version.
≈ “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
Purpose
Prevent invented, stale, redundant, or unjustified dependency changes.
When to activate
An agent proposes a new package, version, import path, or dependency upgrade.
When not to activate
No dependency change is proposed and the task can be completed with existing project capabilities.
Preconditions
- Read applicable repository instructions before edits.
- Preserve unrelated working-tree changes and establish a baseline when the workflow can modify code.
- Identify which tools and environments are actually available; do not claim unavailable checks ran.
Required inputs
- Dependency manifest and lockfile
- Proposed package/import/version
- Runtime/toolchain version
Workflow
- Check whether the needed capability already exists in direct or transitive dependencies or the standard library.
- Verify the package name and import/module mapping using the local environment, lockfile, registry, or official docs.
- Verify the proposed version exists and supports the project's runtime/toolchain constraints.
- Check maintenance, license, security/advisory status, and whether the package is actually necessary for the task.
- Prefer pinned/locked reproducible changes consistent with the repository's package manager.
- Install/update only through the repository's package manager and regenerate its lockfile when authorized.
- Run import/build/tests that prove the dependency is usable.
Relevant tools
Package manager, lockfile, local environment, official registry/docs, advisory scanner when available.
Safety restrictions
Never execute an unreviewed install script outside the package manager or commit registry credentials.
Validation
- Every added name/version is grounded in an observed local or authoritative source.
- Manifest and lockfile remain consistent.
- The dependency is used by the implementation and passes the relevant runtime/build check.
Expected output
- Dependency evidence table
- Manifest/lockfile changes
- Compatibility/security notes
- Executed verification
Failure handling
If registry/network access is unavailable, do not invent a version; use already-locked/local metadata or mark external verification pending.
Completion criteria
The skill is complete only when every applicable validation item above has observed evidence or is explicitly marked not executed with the concrete blocker. Do not replace missing evidence with confidence language.
Research mapping
This skill was selected from research problems: P002, P003, P052. See research/vibe-coding-problems.md and research/problem-evidence.csv in the Vibe Coding Skills repository.
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.

