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 skills add bh-rat/steer --skill building-skillsgit clone --depth 1 https://github.com/bh-rat/steerWrote 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/bh-rat/steer/building-skills)<a href="https://agentmods.dev/skills/bh-rat/steer/building-skills"><img src="https://agentmods.dev/badge/skills/bh-rat/steer/building-skills/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/bh-rat/steer/building-skills"><img src="https://agentmods.dev/badge/skills/bh-rat/steer/building-skills.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 | $0.00106 | $0.01708 |
| Opus 5 | $0.00053 | $0.00854 |
| Sonnet 5 | $0.00021 | $0.00342 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
building-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
building-skills
Build an Agent Skill the deliberate way: design the trigger and the
components with the user, scaffold with steer new, write the body, and
prove the result with steer validate and a real run. The user gets an
installed, spec-valid skill, not a plausible-looking draft.
This skill bundles its own steer runtime at scripts/steer.py for its
flow and learning; authoring the new skill additionally needs the
installed steer CLI, checked below.
Before you start
- Check steer. Run
steer --version. If it is missing, ask the user to install it (uv tool install steer-aiorpip install steer-ai), then continue; do not hand-roll a lookalike scaffold as a fallback. - Set two paths.
SKILLis this skill's own directory (this file's parent);WSis the new skill's directory, decided during design; it does not need to exist yet. - Apply past lessons. Run
python3 "$SKILL/scripts/steer.py" learn showand follow what it says; those lessons came from real previous builds. - Improving rather than building? For a review or tune-up of an
existing skill, skip the flow and follow
references/improving-a-skill.md.
Process
This build runs behind an enforced flow: steps verify themselves against reality, and you cannot skip ahead. The flow lives next to this file and operates on the new skill's directory:
python3 "$SKILL/scripts/steer.py" flow status --workspace "$WS"
python3 "$SKILL/scripts/steer.py" flow next --workspace "$WS"
python3 "$SKILL/scripts/steer.py" flow done <step-id> --workspace "$WS"
The steps, and what completes them:
- design (mandate): triage the source material, make the four
decisions below, and compose the exact
steer newcommand. Show the user the command, the name, and the install scope; mark the step done when they agree. - scaffold (verified): run the agreed command. Completes when SKILL.md exists in the workspace.
- write (verified): fill the scaffold with real content. Completes
when no TODO marker is left anywhere in the workspace (the generated
scripts/steer.pyis exempt; you never edit it). - validate (verified): completes only while
steer validate .passes in the workspace. Fix warnings and info findings too, or tell the user which one stays and why. - exercise (mandate): install the skill, run it once on a real task, and fix what the run exposes. Mark done after the run, then wrap up as the directive says.
What ships with it
6 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.
- 8d ago First seen · 143 lines · 106 tokens per session scan A 95c782f7064f
building-skills is a skill published in the GitHub repository bh-rat/steer (7 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 1,708 once invoked, about $0.0005 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…