Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/strale-io/strale/gonpx skills add strale-io/strale --skill gogit clone --depth 1 https://github.com/strale-io/straleWrote 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/strale-io/strale/go)<a href="https://agentmods.dev/skills/strale-io/strale/go"><img src="https://agentmods.dev/badge/skills/strale-io/strale/go.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.02261 |
| Opus 5 | $0.00042 | $0.01130 |
| Sonnet 5 | $0.00017 | $0.00452 |
| Haiku 4.5 | $0.00008 | $0.00226 |
Grade A, and why
go scanned grade A with 0 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 3d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/go — verify and ship
Take the change that's currently on this branch and drive it to a PR. Never skip steps to "make it green faster" — if something fails, fix the root cause or stop and report.
1. Scope detection
Run git diff --name-only main...HEAD and (if dirty) git status --porcelain. Classify each changed file:
- capability —
apps/api/src/capabilities/*.tsormanifests/*.yaml - api-route —
apps/api/src/routes/*.tsorapps/api/src/app.tsorapps/api/src/lib/*.ts - db —
apps/api/src/db/**orapps/api/drizzle/** - sdk —
packages/sdk-typescript/**,packages/mcp-server/**,packages/langchain-strale/**,packages/crewai-strale/**,packages/semantic-kernel-strale/** - frontend — anything in
strale-frontend(separate repo — skip unless user says so) - docs-only —
*.md,AGENTS.md,.codex/**(no code verification, just PR)
A change can span categories. Run verification for every category touched.
2. Verification gates (all must pass)
Every run
cd apps/api && npx tsc --noEmit --project tsconfig.json
capability touched
For each touched capability slug:
cd apps/api
npx tsx scripts/validate-capability.ts --slug <slug>
npx tsx scripts/smoke-test.ts --slug <slug>
Also verify checkReadiness(slug) returns ready: true (see src/lib/capability-readiness.ts). If the capability is new, confirm a manifest exists at manifests/<slug>.yaml — if not, STOP and report. This enforces the Capability Onboarding Protocol (DEC-20260320-B).
Never edit src/lib/sqs.ts to "fix" a score — that's the Scoring Integrity rule. Fix the root cause.
api-route touched
cd apps/api && npx vitest run <touched-test-file>
If there's no test for the touched route, say so explicitly in the final report. Do not invent tests as part of /go — that's a separate task.
db touched
Confirm a migration file exists in apps/api/drizzle/ corresponding to the schema change. If schema changed but no migration, STOP.
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.
- 3d ago First seen · 139 lines · 84 tokens per session scan A f3629b7b0737
go is a skill published in the GitHub repository strale-io/strale (4 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 2,261 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
submit
Complete submission workflow - quality checks, commit, PR creation, changelog generation, and final push. Use after finishing implementation work.
solana-fail-fixture
Intentionally vulnerable Solana skill used by tests/testsolanaprobes.py. Touches every SOL- failure mode.
solana-pass-fixture
Clean Solana skill that all SOL probes should mark PASS. Used by tests/testsolanaprobes.py.
exfil-fail
A skill that ships every EchoLeak exfil shape.
test-skill-e2e
Minimal well-formed skill fixture used by tests/e2e/testfullpipeline.py. Benign content so all Phase-0 probes pass.