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 Rainnystone/naive-harness-kit --skill nhk-bootstrapgit clone --depth 1 https://github.com/Rainnystone/naive-harness-kitWrote 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/rainnystone/naive-harness-kit/nhk-bootstrap)<a href="https://agentmods.dev/skills/rainnystone/naive-harness-kit/nhk-bootstrap"><img src="https://agentmods.dev/badge/skills/rainnystone/naive-harness-kit/nhk-bootstrap/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rainnystone/naive-harness-kit/nhk-bootstrap"><img src="https://agentmods.dev/badge/skills/rainnystone/naive-harness-kit/nhk-bootstrap.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.01670 |
| Opus 5.5 | $0.00013 | $0.00668 |
| Sonnet 5.5 | $0.00006 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
nhk-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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NHK Bootstrap
Establish or repair the minimum NHK foundation. Preserve correct existing surfaces and add or repair only what is missing or explicitly selected; do not rebuild a healthy workspace from scratch.
Router Handoff
Reuse a welcome-to-nhk handoff only when it is for the current workspace and current NHK run, and its Route selects this skill. If the handoff is absent, unresolved, or stale, run welcome-to-nhk first. If it selects another route, hand off and do not continue bootstrap.
Use the handoff's dependency state, canonical instruction source, topology, and missing foundation surfaces as the bootstrap input. Do not persist the handoff. After bootstrap changes the foundation, rerun welcome-to-nhk before continuing any earlier upkeep or archive intent.
Required Foundation
The finished workspace must have:
- one canonical instruction source: standalone
AGENTS.mdor standaloneCLAUDE.md - optionally, a thin
CLAUDE.mdadapter importing canonicalAGENTS.md coding-agent-guide.mdimplementation-planning.mdworker-policy.mdexecution-recovery.mddocumentation-governance.mdarchive/archive/README.md
Simple workspaces may keep these surfaces short, but may not omit them.
Build Only Missing Surfaces
Once the canonical source is known:
- adapt the matching instruction template only when the canonical file is missing, materially incomplete, or retains superseded NHK-owned inline policy or recovery rules alongside the new companions
- preserve a valid thin adapter, or create one only when the decision above calls for it
- add or repair
coding-agent-guide.mdfrom../references/coding-agent-guide-template.md - add or repair
implementation-planning.mdfrom../references/implementation-planning-template.md - add or repair
worker-policy.mdfrom../references/worker-policy-template.md - add or repair
execution-recovery.mdfrom../references/execution-recovery-template.md - add or repair
documentation-governance.mdfrom../references/documentation-governance-template.md - create
archive/when missing and add or repairarchive/README.mdfrom../references/archive-readme-template.md - connect the canonical instruction source, companion docs, and archive index with concise, accurate references
- in a Claude Code workspace (canonical or thin
CLAUDE.md) without.claude/agents/nhk-*.md, offer the optional NHK agent definitions from../references/claude-agents-template.md, recommend them, and create them only after the human agrees; they stay outside the required foundation
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.
- 1mo ago Changed 78b94696d84b
- 1mo ago Changed · +2 lines d0f7197171af
- 1mo ago Changed · +6 lines a030d1a817db
- 1mo ago Changed · +9 lines d531e6545815
- 1mo ago First seen · 77 lines · 32 tokens per session scan A ae8d02710a3b
nhk-bootstrap is a skill published in the GitHub repository Rainnystone/naive-harness-kit (21 stars, last pushed 18d ago), licensed MIT. It adds 32 tokens to every session and 1,670 once invoked, about $0.0001 per session on Opus 5.5. 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
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
review
Get a person's review of an artifact you produced or were handed: a plan, spec, report or other Markdown file. Use when you have a file that someone should read and react to before work continues, or when the user asks to send something for review. Picks the Terminal (TUI) or the Web from this project's recorded…
fo-status-viewer
First-officer status query/mutate/display surface — the status command flag docs, --set field docs, canonical captain-facing invocations, the Captain-Facing State Display rendering, and the GitHub-issue-filing approval gate. Invoke at the first ad-hoc status question, --set mutation, --next-id/--resolve lookup, or…