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 45ck/skill-harness --skill third-party-skill-intakegit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/third-party-skill-intake)<a href="https://agentmods.dev/skills/45ck/skill-harness/third-party-skill-intake"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/third-party-skill-intake.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00369 |
| Opus 5 | $0.00019 | $0.00185 |
| Sonnet 5 | $0.00008 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
third-party-skill-intake 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.
What it actually says
Third-Party Skill Intake
Use this skill when reviewing a public skill, agent, Cursor rule, plugin, MCP, or agent-workflow repository for possible 45ck adoption.
Process
- Classify the repo type: official reference, curated index, skill pack, rule pack, plugin, MCP/tool pack, workflow framework, task-memory system, or runtime platform.
- Treat stars, forks, and social activity as discovery signals only.
- Verify license, provenance, helper scripts, tool configuration, and install posture before recommending adoption.
- Inventory actual surfaces:
SKILL.md,.cursor/rules/*.mdc,.claude/agents,.codex/agents, plugin manifests, MCP configs, lockfiles, install scripts, generated metadata, and task-state files. - Compare the repo against the first-party 45ck catalog before proposing new skills.
- Map every useful idea to one destination:
- first-party rewrite under
packs/ - harness helper or installer feature
- fixture/test case only
- reference/monitor only
- reject/quarantine
- first-party rewrite under
Output
Repo Type
Surfaces Found
License And Provenance
Risk Flags
Catalog Overlap
Adoption Destination
Rewrite Requirements
Fixture Recommendation
Avoid
- copying whole public catalogs into the harness
- treating README claims as proof of safe behavior
- adding third-party repos to
scripts/dependencies.jsonwithout an explicit ownership decision - installing unreviewed skills globally
- running helper scripts from public repos inside the live install path
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 · 42 lines · 38 tokens per session scan A 1f993a46b014
third-party-skill-intake is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 369 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.
Other skills, from other repositories
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
do-it-core
Use when repository work needs a shared baseline for intent, facts, causal changes, and honest evidence.
do-it-decide
Use when uncertainty about a choice, plan, dependency, or handoff could materially change what gets built.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-skill-authoring
Use when creating or revising a do-it skill so its trigger and unique professional judgment are useful without prescribing ceremony.