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 agentmods add commands/intense-visions/harness-engineering/ideate-fleetgit clone --depth 1 https://github.com/Intense-Visions/harness-engineeringWrote 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/commands/intense-visions/harness-engineering/ideate-fleet)<a href="https://agentmods.dev/commands/intense-visions/harness-engineering/ideate-fleet"><img src="https://agentmods.dev/badge/commands/intense-visions/harness-engineering/ideate-fleet.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 | $0.00140 | $0.00872 |
| Opus 5 | $0.00070 | $0.00436 |
| Sonnet 5 | $0.00028 | $0.00174 |
| Haiku 4.5 | $0.00014 | $0.00087 |
Grade A, and why
harness:ideate-fleet 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 4d 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.
What it actually says
Phases:
- select: Compose the STRATEGY.md tracks and any supplied opportunity areas into a bounded queue of disjoint themes, merging any overlapping pair, and score and order them by strategic weight; stop and report when there is no theme source at all
- confirm: Present the ranked themes with their strategic basis and any disjointness merges, the per-theme candidate count, the objection policy, the per-theme cut and global cap, the novelty lookback window, the pinned UTC batch date, and the proposed concurrency for a single up-front human approval that also restates that nothing will be filed or committed
- dispatch: Fan out worktree-isolated subagents, each running the real harness-ideate pipeline for one theme to its ranked artifact with the interactive stops answered from confirmed policy, then preselecting its top candidates, cross-checking each for novelty against open issues, roadmap rows, and recently-merged PRs with backfill, and collecting the artifact verbatim into the invoking tree before its worktree is released
- verify: Independently resolve each collected artifact by its frontmatter topic, confirm the mandated frontmatter, count semantics, and per-candidate fields, and recompute every base score from the artifact's own inputs to confirm score equality, non-increasing final-score order, and a bounded strategy-alignment tiebreaker — never by subagent self-report, and recording all-OS CI as not applicable to this member
- curate-and-report: Run the cross-theme dedup backstop, apply the bounded cut with its reserved-slot rule, write one curated ranked shortlist for the human to pick from, and report every non-shortlisted outcome with its reason — already-known drops with citations, novelty-unknown annotations, backfills, dedup collapses, below-cut counts, thin themes, parked themes, and rejected themes
<execution_context> @agents/skills/claude-code/ideate-fleet/SKILL.md @agents/skills/claude-code/ideate-fleet/skill.yaml </execution_context>
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.
- 4d ago First seen · 42 lines · 140 tokens per session scan A d4dda577a718
harness:ideate-fleet is a command published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 872 once invoked, about $0.0007 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.