agentmods.dev

strale: Skill for Claude Code

.agents/skills/onboard-capability/SKILL.md

onboard-capability is a skill for Claude Code, Codex from strale-io/strale. It costs 92 tokens per session (1,972 once invoked), scanned A, original, MIT.

A procedure for adding or changing a capability in an application. It follows the project's manifest, data-source, validation, readiness, and smoke-test requirements.

In plain words
What is it for?
Use it to onboard a new executor, manifest, or capability slug and verify that it is ready to run.
Why use it?
It removes guesswork about the required steps and checks when introducing a new capability.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is strale-io/strale's own configuration. It tells Claude Code and Codex how to work on strale itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything strale configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is npx tsx scripts/onboard.ts --manifest ../../manifests/<slug>.yaml --dry-run # preview, no writes.

not rated 5repo yesterday A scan 92 tokens original MIT
View source ↗ strale-io/strale strale.dev
Reuse

Borrowing it

Nothing to install: this file belongs to strale-io/strale. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/strale-io/strale/main/.agents/skills/onboard-capability/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/strale-io/strale

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for onboard-capability

README.md
[![agentmods](https://agentmods.dev/badge/skills/strale-io/strale/onboard-capability/github.svg)](https://agentmods.dev/skills/strale-io/strale/onboard-capability)
Your own site
<a href="https://agentmods.dev/skills/strale-io/strale/onboard-capability"><img src="https://agentmods.dev/badge/skills/strale-io/strale/onboard-capability/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.

agentmods 80×15 button for onboard-capability

Your own site · 80×15
<a href="https://agentmods.dev/skills/strale-io/strale/onboard-capability"><img src="https://agentmods.dev/badge/skills/strale-io/strale/onboard-capability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,972 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.01972
Opus 5.5 $0.00037 $0.00789
Sonnet 5.5 $0.00018 $0.00394
Haiku 4.5 $0.00009 $0.00197

Measured 12d ago against content hash 2aea06562da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

onboard-capability scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -H "Authorization: Bearer $ADMIN_SECRET" "$STRALE_API_URL/v1/internal/onboarding/readiness?slug=<slug>"
.agents/skills/onboard-capability/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/onboard-capability — get a capability through the pipeline

The prompt says what the capability does. This skill is how it enters the system, and that part is not optional because the prompt left it out. Authority: CLAUDE.md → "Capability Onboarding Protocol (DEC-20260320-B)" and "Adding New Capabilities (MANDATORY PIPELINE)". If this file and CLAUDE.md disagree, CLAUDE.md wins; fix this file. The reviewer's checklist is in the root REVIEW.md.

0. Before writing code

  • Read the onboarding spec: Notion page 32467c87-082c-819a-a731-d8a5f7237b33 if Notion is reachable, otherwise the two CLAUDE.md sections above.
  • Data access (DEC-20261023-A). Name the lane the upstream source is in: preferred (official API, licensed data, statutory registry), allowed with checks, or never. A "never" source stops here. Check that the host is not in PROHIBITED_UPSTREAM_HOSTS (apps/api/src/lib/vendor-terms.ts, the list of banned hosts) or tos-blocklist.ts. Record the terms verdict, meaning what permits per-call access or resale, with a link. The manifest has no field for it yet, so put it in a limitations entry (category coverage). For a new vendor, also add it to config/vendors.yaml. That register is a shadow only until M4; the Notion Vendor Roster is still the authority.
  • If the slug is in DEACTIVATED in apps/api/src/capabilities/auto-register.ts, stop and find out why before you reverse it.
  • A compliance data service (sanctions, PEP, UBO, adverse media, registry self-builds) must meet the DEC-20260428-B engineering bar. That is a build Petter decides on, not a routine onboarding.
  • A new vendor credential needs a row in config/env-manifest.yaml (npm run env:check) and a zero-cost health probe in apps/api/src/lib/dependency-manifest.ts (skipAuth: true on paid APIs).

1. Executor — apps/api/src/capabilities/<slug>.ts

  • registerCapability(slug, handler). It is auto-registered at startup; do not import it in app.ts.
  • Return { output, provenance: { source, fetched_at } }, with the acquisition method in provenance.
  • Every external call has AbortSignal.timeout(), and caller-supplied URLs go through safeFetch (CI lints both).
  • On a paid upstream, reject empty, null or sub-2-character input before the call (Principle B).
  • Errors are structured: never raw HTML or a stack trace.

Read the full file on GitHub · 154 lines

Changes

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.

  1. 12d ago First seen · 154 lines · 92 tokens per session scan A 2aea06562da7

Subscribe to this mod's changes

onboard-capability is a skill published in the GitHub repository strale-io/strale (5 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,972 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-25.

Backend and APIsPlanningai-agentsapieu-ai-actmcpqualitytrust
Related

onboard-capability compared with skills from other repositories

onboard-capability next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
onboard-capabilitystrale-io/straleSkill5yesterdayMITA92Claude Code, Codex
jentic-api-scorecardjentic/jentic-api-scorecardSkill222d agoApache-2.0A128Claude Code, Codex
api-rate-limit-handlersickn33/agentic-awesome-skillsSkill49kyesterdayMITA32Claude Code
api-integration-architectsickn33/agentic-awesome-skillsSkill49kyesterdayMITA33Claude Code
dmrwemake-services/django-modern-restSkill1.5ktodayMITA80Claude Code, Codex
horse-mvc-architectureHashLoad/horseSkill1.4k8d agoMITA34Claude Code, Codex
horse-ssl-tlsHashLoad/horseSkill1.4k8d agoMITA24Claude Code, Codex