agentleFS
Sign inStart free
aiconnaiaiconnai/engram/skills/dependency-triage/SKILL.md

dependency-triage

Skill3 starsChanged 10 months agoMITView on GitHub

Use for an Engram dependency triage loop that watches advisories and lockfiles, proposes patch-only updates, rejects major upgrades without approval, and records reproducible verification commands.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. aiconnai/agentshield★ 2190% same

    Wrote their own version · 0

    None found.

    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 repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to watch dependency alerts and propose low-risk patch candidates only.

    line 8
  2. Distinctive:

    Default policy is patch updates only.

    line 43
  3. Distinctive:

    Never run major upgrades without human approval.

    line 44
  4. Distinctive:

    Treat minor upgrades as human-reviewed unless the loop charter explicitly allows them.

    line 45
  5. Very specific:

    If no patch path exists, route to ESCALATE_HUMAN with evidence.

    line 47
  6. Distinctive:

    Always include a reproducible verification command in the output.

    line 48
  7. Distinctive:

    Do not update lockfiles or manifests when the budget guard, denylist, or verifier is missing.

    line 49
  8. Very specific:

    Run the full Engram gate when dependency metadata, CI, scripts, tools, MCP connectors, or agent surfaces change: bash …

    line 51
  9. Distinctive:

    Run targeted security review when dependency changes affect scripts, tools, connectors, generated execution surfaces, or agent-controlled …

    line 53

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dependency Sweeper Triage Loop

Use this skill to watch dependency alerts and propose low-risk patch candidates only. Pair it with skills/loop-engineering/SKILL.md for the global Engram loop guardrails and the full harness gate.

Inputs

  • Advisory feeds, security notices, or Renovate/Dependabot-style inputs.
  • Lockfile and package manager metadata.
  • Current dependency-sweeper-state.md, loop-run-log.md, and loop-budget.md.
  • Relevant release notes or changelogs for candidate patch versions.
  • Current denylist, pause flags, and attempt counts.

Output

Record findings in state:

## High Priority
- Package:
  Current version:
  Target patch version:
  CVE or issue:
  Version window:
  Blast radius estimate:
  Patch strategy:
  Verification command:

## Watch

## Escalate

Rules

  • Default policy is patch updates only.
  • Never run major upgrades without human approval.
  • Treat minor upgrades as human-reviewed unless the loop charter explicitly allows them.
  • If no patch path exists, route to ESCALATE_HUMAN with evidence.
  • Always include a reproducible verification command in the output.
  • Do not update lockfiles or manifests when the budget guard, denylist, or verifier is missing.
  • Run the full Engram gate when dependency metadata, CI, scripts, tools, MCP connectors, or agent surfaces change: bash docs/harness/bin/sensors.sh.
  • Run targeted security review when dependency changes affect scripts, tools, connectors, generated execution surfaces, or agent-controlled code paths.

Patch Candidate Gate

A patch candidate is eligible for L2 only when:

  • The advisory or issue is confirmed.
  • The update is patch-level or explicitly approved.
  • The affected package is not in a denied ecosystem or path.
  • The test/build command is known.
  • Attempts are below 3.
  • The verifier can independently run the proposed verification command.

Completion Gate

Mark the run complete only when high-priority advisories have a patch strategy or escalation, watch items are recorded, and loop-run-log.md includes the evidence source, budget status, and next action.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free