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/rossoctl/examples/skills-scannpx skills add rossoctl/examples --skill skills-scangit clone --depth 1 https://github.com/rossoctl/examplesWhat 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 | $0.00017 | $0.01885 |
| Opus 5 | $0.00009 | $0.00942 |
| Sonnet 5 | $0.00003 | $0.00377 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
skills:scan 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Repository for Skills
Bootstrap skills for a new repo, or audit and update skills in an existing one.
flowchart TD
START(["/skills:scan"]) --> MODE{"Repo has skills?"}
MODE -->|No| NP1["Analyze Repo"]:::skills
MODE -->|Yes| EP1["Validate Existing"]:::skills
NP1 --> NP2["Identify Categories"]:::skills
NP2 --> NP3["Generate Core Skills"]:::skills
NP3 --> NP4["Generate settings.json"]:::skills
NP4 --> DONE([Skills bootstrapped])
EP1 --> EP2["Gap Analysis"]:::skills
EP2 --> EP3["Content Quality"]:::skills
EP3 --> EP4["Connection Analysis"]:::skills
EP4 --> EP5["Usefulness Rating"]:::skills
EP5 --> EP6["Generate Report"]:::skills
EP6 --> EP7["Update README"]:::skills
EP1 -->|Issues| WRITE["skills:write"]:::skills
EP6 -->|Gaps| WRITE
classDef skills fill:#607D8B,stroke:#333,color:white
When to Use
- Setting up Claude Code skills in a new repository
- Auditing an existing repo for skill gaps
- Updating skills after the repo's tech stack or workflows changed
- Onboarding to a new codebase
Mode: New Repo (no .claude/skills/ exists)
Phase 1: Analyze Repository Structure
Scan for technology markers:
ls -la Makefile pyproject.toml package.json Cargo.toml go.mod pom.xml 2>/dev/null
Check CI configuration:
ls .github/workflows/ .gitlab-ci.yml Jenkinsfile .circleci/ 2>/dev/null
Check deployment patterns:
ls -d charts/ helm/ k8s/ kubernetes/ deployments/ docker-compose* Dockerfile 2>/dev/null
Check test structure:
find . -type d -name "tests" -o -name "test" -o -name "__tests__" -o -name "e2e" 2>/dev/null | head -10
Phase 2: Identify Skill Categories
Based on findings, propose categories:
| Marker | Suggested Skills |
|---|---|
.github/workflows/ |
CI-related skills (status, monitoring) |
charts/ or helm/ |
Helm debugging skills |
Dockerfile |
Docker build/debug skills |
tests/e2e/ |
TDD and RCA skills |
deployments/ansible/ |
Ansible deploy skills |
| Kubernetes manifests | K8s health, pod, and log skills |
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 · 244 lines · 17 tokens per session scan A c0d4013adf34
skills:scan is a skill published in the GitHub repository rossoctl/examples (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,885 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.