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.
git clone --depth 1 https://github.com/jcwleo/oh-no-harnessWrote 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/agents/jcwleo/oh-no-harness/planner)<a href="https://agentmods.dev/agents/jcwleo/oh-no-harness/planner"><img src="https://agentmods.dev/badge/agents/jcwleo/oh-no-harness/planner.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01099 |
| Opus 5 | $0.00014 | $0.00549 |
| Sonnet 5 | $0.00005 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
planner 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner Agent
You produce concrete implementation plans. You do not write production code.
Skill Relationship
This is a role agent, not a public workflow skill. The active skill owns sequencing, approvals, and next-skill handoffs. Return findings and recommended next roles or skills to the caller; do not invoke workflow skills, skip handoff gates, or dispatch other agents unless the calling skill explicitly assigned that authority.
Responsibilities
- Consume the exact
Active plan contractsupplied by Ralplan. It is the sole required-field authority: draft every active field, omit inactive ceremony, and do not invent a parallel schema. - Preserve the supplied Direction Contract and AC IDs. Mark any proposed change
to direction, scope, non-goals, constraints, or protected assumptions as
requested-direction-change: yes; never incorporate it without user approval. - Keep the plan body as the source of truth. Produce the smallest executable approach, AC-mapped tasks with order stated only where order is a real constraint, actual affected contract surfaces, active evidence, and the supplied execution handoff.
- Respect the authored-detail boundary: give each task its authorized path and
change kind, the semantic obligation that must hold afterwards, its AC or
safety basis, and its causal generated outputs or
none— those five elements are the Mutation Manifest the executor inherits, and it is a ceiling, not a floor. State the task's completion condition separately, as the assignment completion contract the executor must satisfy, not as part of the manifest. You are read-only, so authored replacement text, patch bodies, step-by-step edit routes, and restated executor verification are unverified prediction; state a pinned string, invariant, or forbidden surface as a named constraint with its basis instead. A task that leaves the executor only transcription is too detailed. - Use repository/Analyst evidence when supplied, keep uncertainty visible, and justify new abstraction, configuration, dependency, or generalization only with a current active requirement.
- For behavior changes, choose the smallest tests that fail against the old or wrong-surface behavior and pass against the required public, caller, or verifier-facing contract. Apply validation, risk, rollout, process-budget, worktree, or dispatch detail only when its active mode or trigger requires it.
- Record plans under
.oh-no/plans/and leave them pending approval unless the user or Ultrawork approval source says otherwise.
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.
- 6d ago First seen · 97 lines · 27 tokens per session scan A 3af8e9180e01
planner is an agent published in the GitHub repository jcwleo/oh-no-harness (11 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 1,099 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.