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/andr-ca/agentharness/project-bootstrapnpx skills add andr-ca/agentharness --skill project-bootstrapgit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00064 | $0.01139 |
| Opus 5 | $0.00032 | $0.00570 |
| Sonnet 5 | $0.00013 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
project-bootstrap 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Bootstrap
Use this the first time the harness runs in a project, or whenever the owner asks you to set it up, tailor it, or figure out which conventions apply here.
The deterministic work is done by agentharness bootstrap. Your job is
the conversation — the tool inventories the repository and lists the
decisions that need making; you ask the owner about them, one at a time,
and feed the answers back.
Check the command exists first: agentharness bootstrap plan --help.
If it is unavailable, this repository has not installed the harness CLI —
fall back to tools/setup/harness-link.sh and assess the project
conversationally rather than claiming a bootstrap flow exists.
The loop
# 1. Inventory (read-only — writes nothing, safe to run any time)
agentharness bootstrap plan --json
# 2. Feed answers back as you collect them
agentharness bootstrap plan --answer rigor.tier=production
# 3. Apply, only with the hash of the plan the owner approved
agentharness bootstrap apply --answer ... --confirm <plan_hash>
plan is safe to re-run at any point. Re-run it after every answer — the
question set and the proposed actions both change as answers come in.
Reading the plan
{
"detected": [{"capability": "test", "present": true,
"detail": "pytest", "evidence": ["pyproject.toml"]}],
"questions": [{"id": "rigor.tier", "prompt": "...", "default": "production"}],
"actions": [{"path": "ruff.toml", "summary": "Create ruff.toml"}],
"is_resolved": false,
"plan_hash": "..."
}
| Field | What it means |
|---|---|
detected |
Verified facts. present: true means a config file says so, and evidence names it. |
questions |
Decisions only the owner can make. Unanswered ones block apply. |
actions |
Exactly what apply would create. Empty until answers ask for something. |
is_resolved |
False while any question is unanswered. |
plan_hash |
Changes whenever the repo or the answers change. |
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 · 130 lines · 64 tokens per session scan A 1d4c6fafc58e
project-bootstrap is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 1,139 once invoked, about $0.0003 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
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…