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 NiroDu/claude-code-harness-kit --skill claude-harness-wrap-upgit clone --depth 1 https://github.com/NiroDu/claude-code-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/nirodu/claude-code-harness-kit/claude-harness-wrap-up)<a href="https://agentmods.dev/skills/nirodu/claude-code-harness-kit/claude-harness-wrap-up"><img src="https://agentmods.dev/badge/skills/nirodu/claude-code-harness-kit/claude-harness-wrap-up/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/nirodu/claude-code-harness-kit/claude-harness-wrap-up"><img src="https://agentmods.dev/badge/skills/nirodu/claude-code-harness-kit/claude-harness-wrap-up.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.00596 |
| Opus 5 | $0.00026 | $0.00298 |
| Sonnet 5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
claude-harness-wrap-up 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Harness Wrap-Up
Use this skill when work is ending in a repository that uses claude-code-harness-kit.
This skill is for the final phase only. It does not replace initialization or state recovery. Use it after implementation, investigation, or planning work when the repo artifacts should be updated so the next session can resume cleanly.
Core rule
Do not end the task with knowledge trapped only in chat. Move durable state back into the repository artifacts when appropriate.
Wrap-up workflow
- Identify what actually changed in this task.
- Identify what verification actually ran.
- Update the configured state file from
docs/harness-config.json:statusblockersnextSteplastUpdatedverification.lastCommandverification.lastResultverification.notes
- If the task produced an important implementation decision, append it to the configured decisions file.
- If the task revealed a durable team preference, workflow convention, or recurring pitfall, add it to the configured project memory file.
- If the contract changed materially, update the active contract before finishing.
- In the final response, state:
- what changed
- what verification ran
- what did not run
- current blockers
- next step
Decision rules
Update harness-state on every meaningful task closeout.
Update decisions.md when:
- the team made a choice that future work should follow
- a tradeoff was chosen over another valid path
- a fix depends on a non-obvious rationale
Update project-memory.md when:
- the repo has a durable preference
- there is a recurring gotcha
- there is a workflow expectation future sessions should remember
Update the contract when:
- scope changed
- acceptance changed
- the implementation plan changed enough that future work would be misled
Honesty rules
- Never claim verification ran if it did not.
- Never say "done" without noting the unverified parts when checks were skipped.
- If no files were updated because there was nothing durable to record, say that explicitly instead of pretending a write happened.
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 · 80 lines · 51 tokens per session scan A eafbd2383476
claude-harness-wrap-up is a skill published in the GitHub repository NiroDu/claude-code-harness-kit (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 596 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.