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 OutlineDriven/odin-claude-plugin --skill watch-for-harness-modegit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/watch-for-harness-mode)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/watch-for-harness-mode"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/watch-for-harness-mode/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/outlinedriven/odin-claude-plugin/watch-for-harness-mode"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/watch-for-harness-mode.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 | $0.00044 | $0.00981 |
| Opus 5 | $0.00022 | $0.00491 |
| Sonnet 5 | $0.00009 | $0.00196 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
watch-for-harness-mode 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch for harness mode
Contract
| Field | Bound contract |
|---|---|
| Trigger | A watch pattern has proven itself and the user wants to turn it into a reusable harness. |
| Authority | Reversible local write only: write only the named harness artifact file. No VCS commit, no remote call, no credential use, no published artifact. Rollback: delete or revert the harness artifact. |
| Side effect | One harness artifact as a reversible local state change. |
| Done | A reusable harness is created from the proven watch. |
Inputs
- Watch transcript (required): the proven watch pattern: a session transcript, run log, artifact, or notes that document the watch's target, interval, evaluation logic, completion predicate, and observed success.
- Harness name (required): a slug for the harness artifact file.
- Harness description (optional): a one-sentence description of what the harness checks and when it succeeds. Defaults to "Reusable harness derived from a proven watch pattern."
- Default poll interval (optional): the polling interval in seconds. Defaults to the interval observed in the watch transcript, or 60 if unspecified.
- Default deadline (optional): the maximum polling duration in seconds. Defaults to the deadline observed in the watch transcript, or 300 if unspecified.
- Adoption confirmation (required): the user explicitly confirms or declines to adopt the harness artifact.
Procedure
- Validate inputs. Reject if the watch transcript is absent or contains no observable target, completion predicate, or evaluation logic. Stop if the harness name is absent or contains path-separator characters. Done when: inputs are validated, or the step has stopped on ambiguous inputs.
- Bound scope. The harness artifact is the only write target. No VCS commit, no remote call, no credential use, no published artifact. If the harness name already exists as a file in the working directory, stop and report the collision. Done when: scope is bounded and no name collision exists.
- Extract the watch mechanism from the transcript: (a) the target surface being watched, (b) the completion predicate that determined success, (c) the evaluation logic that applied the predicate, (d) the poll interval, and (e) the deadline. Done when: all five elements are extracted, or the step has stopped reporting the missing element.
- Synthesize the harness. Write a harness artifact named
{harness-name}.md(or the user's preferred extension) containing: the harness name, the extracted description or default, the extracted target, the extracted completion predicate, the extracted evaluation logic, configurable input fields for the target, completion predicate, poll interval, and deadline with their extracted defaults, and the adoption confirmation step. Done when: harness artifact is written with all extracted elements and configurable fields. - Present for adoption. Show the harness artifact to the user. Ask for explicit confirmation or declination. Do not assume adoption. Done when: user response is received.
- Confirm or withdraw. If the user confirms: mark the harness as adopted and report success. If the user declines: delete the harness artifact and report withdrawal. If the user requests modifications: record the requested changes and stop. This skill produces an initial draft, not an iterative editor. Done when: adoption is confirmed, withdrawal is completed, or modification request is recorded and the step has stopped.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 44 lines · 44 tokens per session scan A 445c0b6b079a
watch-for-harness-mode is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 981 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…