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/furedea/agent-harness/example-skillnpx skills add furedea/agent-harness --skill example-skillgit clone --depth 1 https://github.com/furedea/agent-harnessWhat 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 | $0.00012 | $0.00028 |
| Opus 5 | $0.00006 | $0.00014 |
| Sonnet 5 | $0.00002 | $0.00006 |
| Haiku 4.5 | $0.00001 | $0.00003 |
Grade A, and why
example-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 yesterday.
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.
What it actually says
Example skill
Exercise provider-specific skill rendering.
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.
- yesterday First seen · 9 lines · 12 tokens per session scan A 04b236e0104d
example-skill is a skill published in the GitHub repository furedea/agent-harness (1 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 28 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 2026-08-31.
Other skills, from other repositories
issue-tdd
Use when converting a rough goal, roadmap item, bug report, or underspecified GitHub issue into an implementation-ready issue with acceptance criteria, non-goals, validation, and user decision questions before code changes.
repo-map-query
Use before broad repository exploration when the relevant files are not already obvious; query a compact generated repo map and open only the top likely files.
issue-driven-development
Use when taking a scoped GitHub issue, review finding, roadmap item, or bug report through implementation, validation, PR/CI, merge, cleanup, and optional learning capture.
review-learning-candidates
Use when reviewing accumulated .agents/learning candidates, deduplicating them, rejecting weak ones, or promoting strong ones into executable checks, hooks, skills, or docs.
capture-learning-candidate
Use at the end of high-signal work to record one compact reviewed learning candidate, without scanning candidate bodies or editing CLAUDE.md, skills, hooks, or invariants directly.
nix-review-ledger-batch
Use for processing review findings or backlog items in small validated batches while keeping status artifacts accurate.