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-upkeepgit 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-upkeep)<a href="https://agentmods.dev/skills/rainnystone/naive-harness-kit/nhk-upkeep"><img src="https://agentmods.dev/badge/skills/rainnystone/naive-harness-kit/nhk-upkeep/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-upkeep"><img src="https://agentmods.dev/badge/skills/rainnystone/naive-harness-kit/nhk-upkeep.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 | $0.00033 | $0.01158 |
| Opus 5 | $0.00016 | $0.00579 |
| Sonnet 5 | $0.00007 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
nhk-upkeep 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 3d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NHK Upkeep
Use this skill only after the NHK foundation exists. It repairs active references and state descriptions; it does not bootstrap missing surfaces or perform an archive transition.
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 upkeep.
Use the handoff's dependency, instruction, topology, and complete-foundation state as the maintenance input. Do not persist the handoff or repeat the topology decision inside upkeep.
Maintenance Pass
- Compare the canonical instruction source and any thin adapter with the live workspace. If its structure needs repair or it retains superseded NHK-owned inline policy or recovery rules alongside the new companions, open only the matching
../references/AGENTS-template.mdor../references/CLAUDE-template.md. - Compare the single Task Routing table in
coding-agent-guide.mdwith current task routes, likely change surfaces, and targeted verification; keep the file at or below 80 lines. Open../references/coding-agent-guide-template.mdonly when this surface needs structural repair. - Compare
implementation-planning.mdwith the Superpowers-compatible task contract; keep it at or below 80 lines and load it only for plan work. Open../references/implementation-planning-template.mdonly when this surface needs structural repair. - Compare
worker-policy.mdwith its on-demand dispatch and review contract; keep it at or below 100 lines. Open../references/worker-policy-template.mdonly when this companion needs contract comparison or repair, not for unrelated upkeep. - Compare
execution-recovery.mdwith its on-demand exhausted-loop contract; keep it at or below 80 lines. Open../references/execution-recovery-template.mdonly when this companion needs contract comparison or repair, not for unrelated upkeep. - Compare
documentation-governance.mdwith actual document roles, active surfaces, workspace/document map, lifecycle, naming/loading rules, and archive invariants; keep it at or below 100 lines. Open../references/documentation-governance-template.mdonly when this surface needs structural repair. - Verify
archive/README.mdremains a resolvable index of existing archived workstreams. Open../references/archive-readme-template.mdonly when its shape or row contract needs repair. - Inspect existing implementation plans, task lists,
task_plan.md,progress.md, andfindings.mdas active surfaces, not permanent assumptions. - Repair inaccurate active references and status descriptions, replace any Claude companion
@import with a literal on-demand path, then verify cross-links and instruction structure.
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.
- 3d ago Changed · +5 lines ee00d0183306
- 9d ago First seen · 53 lines · 33 tokens per session scan A db3b300557ec
nhk-upkeep is a skill published in the GitHub repository Rainnystone/naive-harness-kit (21 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 1,158 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
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…
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.
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.
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…
passdown-intake
Use when processing captured notes/ideas from an inbox into actionable work — scans inbox notes, clarifies intent with the user, routes each note to its target repo, creates a planning artifact (e.g. an OpenSpec change), and marks the note processed.