agentleFS
D-SheyD-Shey/autoharness/.agents/skills/regression-sentinel/SKILL.md

regression-sentinel

Skill10 starsChanged yesterdayMITView on GitHub

Pre-flight and post-flight test suite baseline verification with automatic rollback on test failures

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. Distinctive:

    Use during autonomous or batch task execution loops to protect codebase integrity by catching test regressions immediately and reverting …

    line 9
  2. Distinctive:

    Check clean git working tree state or save SHA/stash.

    line 13
  3. Very specific:

    Run baseline test suite command via autoharness sentinel run --pre-flight (or fast smoke test).

    line 14
  4. Very specific:

    Use autoharness sentinel snapshot to checkpoint clean states.

    line 17
  5. Very specific:

    Run full regression test suite via autoharness sentinel run.

    line 19
  6. Distinctive:

    Verify AST anti-shim checks and test pass rate.

    line 20
  7. Distinctive:

    If regression is detected:

    line 21
  8. Distinctive:

    Test clean state approval: run verification on passing code, verify status passes.

    line 29
  9. Distinctive:

    Test regression rejection: introduce an intentional syntax error or failing assertion, verify sentinel triggers rollback and returns …

    line 30

≈ “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.

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

Regression Sentinel

When to use

Use during autonomous or batch task execution loops to protect codebase integrity by catching test regressions immediately and reverting destructive modifications.

Steps

  1. Capture pre-flight baseline:
    • Check clean git working tree state or save SHA/stash.
    • Run baseline test suite command via autoharness sentinel run --pre-flight (or fast smoke test).
  2. During task execution:
    • Allow modifications within task workspace boundary.
    • Use autoharness sentinel snapshot to checkpoint clean states.
  3. Post-flight verification:
    • Run full regression test suite via autoharness sentinel run.
    • Verify AST anti-shim checks and test pass rate.
  4. If regression is detected:
    • Perform atomic rollback via autoharness sentinel rollback (git restore and clean untracked files).
    • Log the failure reason into .autoharness/sentinel.json and .autoharness/drive_state.json.
    • Prevent downstream corrupted state from propagating.
  5. If verification succeeds:
    • Approve state for commit and milestone completion.

How to verify

  1. Test clean state approval: run verification on passing code, verify status passes.
  2. Test regression rejection: introduce an intentional syntax error or failing assertion, verify sentinel triggers rollback and returns non-zero.

Facts found here

  • Automated safety rollbacks eliminate the need for manual intervention during autonomous overnight runs.
  • Running AST Anti-Shim detection alongside test execution prevents fake "passing" suites caused by empty mocks.

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.