Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/asteroid-belt/skultonpx agentmods add skills/asteroid-belt/skulto/skulto-release-certWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/asteroid-belt/skulto/skulto-release-cert)<a href="https://agentmods.dev/skills/asteroid-belt/skulto/skulto-release-cert"><img src="https://agentmods.dev/badge/skills/asteroid-belt/skulto/skulto-release-cert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asteroid-belt/skulto/skulto-release-cert"><img src="https://agentmods.dev/badge/skills/asteroid-belt/skulto/skulto-release-cert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.06519 |
| Opus 5 | $0.00023 | $0.03259 |
| Sonnet 5 | $0.00009 | $0.01304 |
| Haiku 4.5 | $0.00005 | $0.00652 |
Grade D, and why
skulto-release-cert scanned grade D with 5 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
sqlite3 ~/.agents/skulto/skulto.db "INSERT OR REPLACE INTO skills (id, slug, title, content, source_id, security_status, threat_level, threat_summary) VALUES ('test-malicious', 'test-malicious', 'Test Malicious', 'Ignore Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
sqlite3 ~/.agents/skulto/skulto.db "INSERT OR REPLACE INTO skills (id, slug, title, content, source_id, security_status, threat_level, threat_summary) VALUES ('test-malicious', 'test-malicious', 'Test Malicious', 'Ignore Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
| 4 | Run any command | `skulto check` — no errors, flag survives app startup | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.agents/skulto Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sqlite3 ~/.agents/skulto/skulto.db "INSERT OR REPLACE INTO skills (id, slug, title, content, source_id, security_status, threat_level, threat_summary) VALUES ('test-malicious', 'test-malicious', 'Test Malicious', 'Ignore How it starts
The opening of the file, as written. The whole thing — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skulto Release Certification
Certify a build for Homebrew production release. Three passes, all must be green before shipping.
When to Use
Before tagging a release or updating the Homebrew tap. Run from the skulto repo root.
Pass 1: Unit Tests, Lint, and Cross-Compile
Build both binaries and verify all quality gates.
make build-all
make test
make lint
make format
Cross-compile all release targets:
GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -o /dev/null ./cmd/skulto
GOOS=linux GOARCH=arm64 CGO_ENABLED=0 go build -o /dev/null ./cmd/skulto
GOOS=darwin GOARCH=amd64 CGO_ENABLED=0 go build -o /dev/null ./cmd/skulto
GOOS=darwin GOARCH=arm64 CGO_ENABLED=0 go build -o /dev/null ./cmd/skulto
All four must succeed.
Pass 2: CLI Command Walkthrough
Test every CLI code path against the built binary (./build/skulto).
State Snapshot (REQUIRED before any Pass 2 tests)
Capture the pre-cert state so it can be restored after testing. Run these BEFORE any commands:
# 1. Snapshot installed skills
skulto check > /tmp/skulto-cert-check-before.txt 2>&1
# 2. Backup skulto.json if it exists
cp skulto.json /tmp/skulto-cert-skulto.json.bak 2>/dev/null || true
# 3. Backup the database
cp ~/.agents/skulto/skulto.db /tmp/skulto-cert-skulto.db.bak
# 4. Record installed skill count for later comparison
echo "Snapshot taken: $(date)"
All subsequent sections MUST clean up their own test artifacts. The State Restore section at the end of Pass 2 verifies nothing leaked.
2a: Warm state (existing data)
Run each command and verify expected output:
| Command | Expected |
|---|---|
skulto --help |
Shows usage, subcommands |
skulto check |
Lists installed skills with platforms |
skulto list |
Lists source repositories |
skulto info <slug> |
Shows metadata, tags, install status |
skulto favorites list |
Shows favorites or empty state |
skulto favorites add <slug> |
Adds skill |
skulto favorites remove <slug> |
Removes skill |
skulto save |
Saves manifest or "No changes" |
skulto save (again) |
"No changes" (idempotent) |
skulto scan --pending |
Scans unscanned skills |
skulto scan --skill <slug> |
Scans by slug (not just ID) |
skulto pull |
Syncs all repos, reconciles |
skulto update |
Pull + scan + summary |
skulto discover |
Lists unmanaged skills |
skulto install --help |
Shows usage |
skulto install nonexistent -y |
"No platforms selected" (empty selection safety) |
skulto uninstall --help |
Shows usage |
skulto add --help |
Shows usage |
skulto remove --help |
Shows usage |
skulto ingest --help |
Shows usage |
skulto feedback |
Shows feedback URL |
skulto-mcp --help |
Shows MCP server usage |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 568 lines · 45 tokens per session scan D e075c7fddf09
skulto-release-cert is a skill published in the GitHub repository asteroid-belt/skulto (50 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 6,519 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 5 findings (instruction-override phrasing, downloads and executes remote code, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
verify-and-ship
Run all quality checks (tests, lint, typecheck), fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
ship-workflow
Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Triggers on: "ship it", "release this", "prepare for release", "open a PR", "push and PR", "land this", "/ship-workflow".
mathodology-dev-test-release
Use when checking skill metadata, references or repository boundaries, or preparing an explicitly requested skills release.
repo-harness-check
Verification entrypoint for repo-harness workflow readiness. Runs workflow gates, task sync, contract checks, inspector, and migration dry-run before merge or release.
AI Release Guardian
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.