sample-skill

A test fixture for checking whether a SkillForge validator correctly reads and validates skill configuration files.

In plain words
What is it for?
Running validator tests and confirming that the sample skill produces no errors.
Why use it?
It reveals whether the validator handles boolean settings, lists of allowed tools, and nested metadata without changing their types.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/tripleyak/skillforge/sample-skill
Any agent
npx skills add tripleyak/SkillForge --skill sample-skill
Clone the repo
git clone --depth 1 https://github.com/tripleyak/SkillForge

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.00339
Opus 5 $0.00020 $0.00169
Sonnet 5 $0.00008 $0.00068
Haiku 4.5 $0.00004 $0.00034

Measured 2d ago against content hash b00c169899b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sample-skill 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 2d 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.

scripts/tests/fixtures/sample-skill/SKILL.md · 50 lines

What it actually says

Sample Skill

A fixture skill used by test_validate_skill.py. It uses every frontmatter feature the vendored YAML parser must support, and satisfies every structural check in validate_skill.py, so the full validator must report zero errors for it.

Process

  1. Run the validator against this directory.
  2. Assert that the error list is empty.
  3. Assert that typed values survived parsing (booleans stay booleans).
Step Check Expected
1 frontmatter parse no error
2 user-invocable bool True
3 allowed-tools list of 3 tools

Verification

  • validate_skill.py reports zero errors
  • quick_validate.py reports the skill as valid
  • user-invocable parsed as a boolean

Anti-Patterns

  • Do not pin a dated model ID in frontmatter.
  • Do not duplicate reference content in collapsible details blocks.

Extension Points

  • Add hooks frontmatter once the vendored parser grows hook fixtures.
  • Add a scripts/ directory to exercise script lint checks.
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. 2d ago First seen · 50 lines · 40 tokens per session scan A b00c169899b2

Subscribe to this mod's changes

sample-skill is a skill published in the GitHub repository tripleyak/SkillForge (884 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 339 once invoked, about $0.0002 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.