Loading the registry…
Coordinate multi-agent, multi-worktree coding sessions with durable planning files so in-flight work survives /clear, crashes, compaction, and dead subagents. Reach for it the moment you SPAWN OR COORDINATE SUBAGENTS, split work across MULTIPLE GIT WORKTREES, or share one repo with other people or agents at once — the distinct value is a coordinator-owned subagents.md registry that RECOVERS a subagent that died mid-task, per-worktree file isolation, and per-actor section ownership. Also works for plain single-actor planning of a long, multi-step task (plan.md / in-progress.md / done.md that outlive a context reset) — but that is the secondary case; don't bureaucratize a one-liner. Trigger on "coordinate subagents", "parallel worktrees", "recover the agent that died", session hand-off, or any long multi-agent build; also "plan this out" / "don't lose state" for a real multi-step solo task. Do not trigger for single-step edits, quick one- or two-file changes, or one-off questions.
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
378 critical findings reported by cisco-skill-scanner, agent-audit-kit, 123 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- agents-planning-with-files
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- agents-planning-with-files ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
Incomplete run
0 findings · 0.8s
v2.0.11
3923 findings · 243.2s
v0.3.26
342 findings · 58.9s
v0.1.0
3 findings · 25.7s
v0.1.0
29 findings · 25.8s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image, nerlo-multi-source.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 14, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
This review has not run for this scan yet. It runs once per scan, in the background, and is kept; it appears here when it has. Until then all 4,297 findings above stand exactly as their scanners reported them, at full severity.