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 spences10/my-pi --skill create-harnessgit clone --depth 1 https://github.com/spences10/my-piWrote 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/spences10/my-pi/create-harness)<a href="https://agentmods.dev/skills/spences10/my-pi/create-harness"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/create-harness.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00585 |
| Opus 5 | $0.00020 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
create-harness 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess and Create Harness
A harness must be earned by an approved assessment. Do not turn candidate capabilities directly into an execution contract.
Use threshold
Start assessment when work may benefit from an enforceable execution contract because it has material risk, unresolved scope, destructive effects, or complex coordination. Good candidates include broad uncertain refactors, migrations, deployments, risky releases, external side effects, and explicit user requests.
Use direct work for bounded, low-risk tasks that standard validation can verify. A simple ambiguity may need only a clarifying question.
Workflow
- Call
harness_assessbefore repository mutation. Call it by itself. - Recover context with the remaining read-only tools.
- Establish source of truth from concrete source, tests, docs, history, and observed behavior.
- Find existing Pi, package, project, or platform primitives before proposing a new capability.
- Challenge assumptions. Record rejected options and why the evidence rejects them.
- Define the smallest useful vertical slice or falsifiable experiment.
- Call
harness_assessment_submitwith one recommendation:directfor bounded work;harnesswhen an execution contract adds value;rejectwhen the work has not earned adoption.
- For a harness recommendation, include explicit allowed paths and validation commands in the proposed contract.
- Wait for direct user approval. Do not infer approval from agent text or continue implementation while approval is pending.
- The extension creates and activates an approved harness
atomically. Run it with the
execute-harnessskill. Harness approval does not authorize Factory; use Factory only after a direct user request to evaluate it. Do not callharness_createto bypass assessment.
Scope changes
Use harness_amend for bounded changes inside an approved capability.
A new capability, architecture decision, or outer-policy expansion
requires another assessment.
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.
- 7d ago First seen · 72 lines · 41 tokens per session scan A c2176517cd86
create-harness is a skill published in the GitHub repository spences10/my-pi (118 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 585 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
pi
Use when needing a minimal, extensible terminal AI coding agent harness in TypeScript with plugin architecture. Pi: minimalist terminal AI coding agent emphasizing simplicity and composability.
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
optimization
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.