Is experiment safe to install?

SaferSkills independently audited experiment (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

.claude/skills/experiment/SKILL.md · 1 file

.claude/skills/experiment/SKILL.md2.2 KB · Markdown

name: experiment

description: Use to run an autoresearch-style experiment loop — improve a measurable artifact by trying changes, measuring against one objective metric, keeping if better and reverting if not, on an isolated git branch with a logged trail. Trigger on "/experiment", "run an experiment loop", "autoresearch X", "tune/optimize X against a metric", "hill-climb X". Follows references/sops/experiment-loop.md. Enforces the autonomy gate (objective metric + reversible sandbox + no PHI/external) before any unsupervised looping.

Experiment loop (autoresearch)

Hill-climb a measurable artifact: try → measure → keep-or-revert → log, on a branch, with a trail. Full procedure: references/sops/experiment-loop.md. Existing examples + use-case cards: experiments/.

First, the autonomy gate

Before looping unsupervised, confirm all three:

Objective, cheap, automatable metric (code computes it in seconds–minutes).
Reversible sandbox (git branch / throwaway data / .tmp).
No PHI, no confidential data, no external send, no prod deploy.

If any fails → human-in-the-loop: propose each change, get approval, no overnight run. Regulated/production outcomes feed the human-reviewed change process — never auto-deploy. This is CLAUDE.md's scale-caution-to-stakes rule.

Run it

Pick or write the experiment's CARD.md (objective, metric+direction, the one mutable surface, budget, autonomy, owner). New ones can copy experiments/forecast-tuning/.
git checkout -b experiments/<tag>.
Baseline run → tools/experiment_log.py add <results.tsv> --id ... --metric ... --status keep --note baseline.
Loop: edit the one mutable surface → run the read-only harness → log → keep (commit) if improved, else git reset. Simpler-and-equal = keep.
Stop on interrupt or the budget. Hand the winner + trail to the human.

Guardrails

The eval harness is read-only ground truth — never edit it to game the metric.
One mutable surface only (reviewable diffs).
Run artifacts (results.tsv, run.log, data/) are git-ignored; the harness + surface + CARD are the tracked blueprint.
Don't ship regulated/production changes from the loop.

experiment— agent skill

Is experiment safe to install?

Experiment loop (autoresearch)

First, the autonomy gate

Run it

Guardrails

Audit the pieces. Scan the whole. Decide.