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 skills/igovet/codex-cortex-orchestrator/knowledge-harvestnpx skills add igovet/codex-cortex-orchestrator --skill knowledge-harvestgit clone --depth 1 https://github.com/igovet/codex-cortex-orchestratorWrote 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/igovet/codex-cortex-orchestrator/knowledge-harvest)<a href="https://agentmods.dev/skills/igovet/codex-cortex-orchestrator/knowledge-harvest"><img src="https://agentmods.dev/badge/skills/igovet/codex-cortex-orchestrator/knowledge-harvest.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 | $0.00039 | $0.01802 |
| Opus 5 | $0.00019 | $0.00901 |
| Sonnet 5 | $0.00008 | $0.00360 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
knowledge-harvest 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 today.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Harvest
Build a durable functional map of the repository, not a task journal or recent commit summary. Documentation should let a new engineer discover each in-scope capability, its owning code, runtime behavior, and verification or operating path.
Before planning or delegating a harvest, read feature-census.md completely. Its inventory, coverage, page-content, and validation rules are the evidence contract.
The coordinator uses this contract to create delegations, but never performs the census, source or documentation inspection, technical synthesis, writing, or verification itself. Every repository read, project analysis, documentation change, command, and completeness check is worker-owned and returned by report ID.
The orchestrator's closed knowledge-route exception still permits only non-shell direct reads of already-known exact allowed paths. Graph/search and repository-native enumeration described below are worker instructions, never coordinator tools. Unknown roots or paths and every project-local artifact or state check require a worker delegation.
Use the orchestrator's authoritative delegation knowledge contract for every harvest worker. A missing or unreadable project knowledge index justifies a bounded census delegation and never coordinator source inspection. A worker's evidence that supplied documentation is stale, conflicting, or incomplete drives only task-relevant corrective ownership; it does not by itself widen the harvest scope.
Modes
- Harvest: Maintain a complete baseline. If no current source-backed coverage manifest establishes that the feature registry covers the repository, perform a full census. With a credible baseline, inspect changed and impacted surfaces and reconcile them against the complete inventory.
- Harvest refresh: Rebuild the inventory from current source without trusting prior coverage claims, audit every project and feature document, and run an independent post-write completeness review. Finish only when a second planning comparison proposes no factual changes or new feature page.
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.
- today Changed · -1 lines 8bd0711787b6
- 5d ago First seen · 182 lines · 39 tokens per session scan A 03176523a1e9
knowledge-harvest is a skill published in the GitHub repository igovet/codex-cortex-orchestrator (1 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,802 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 2026-08-31.
Other skills, from other repositories
bug-triage
Triage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.
ao-desktop-dev
Launch, restart, or troubleshoot the real AO Electron desktop app from this repository; run a checkout against isolated or real local AO data; combine PR branches for local UI review; and diagnose stale Electron processes, port conflicts, or preload bridge mismatches. Use whenever asked to run, open, show, or visually…
using-ao
Catalog of the AO (Agent Orchestrator) ao CLI: spawning workers, managing sessions and projects, sending messages, controlling the shared browser, previewing pages, and daemon control. Use when using the ao CLI, spawning workers, or managing AO sessions in an AO workspace.
summon
Autonomous orchestrator for manifest work items through the development lifecycle. Use when running egregore to process a backlog automatically.
model-router
当需要调度不同模型执行子任务时使用。根据任务类型匹配模型能力，自动选择最优模型并生成调用指令。TRIGGER: 模型调度、model dispatch、选模型、分派任务、多模型协作、路由到模型.
dev-flow
Assess bounded Codex software development requests before choosing direct work or Dev Flow, then provision confirmed Dev Flow Tasks in dedicated Git worktrees. It may be selected implicitly or explicitly with $dev-flow-codex:dev-flow; the selector never skips assessment. Explicit Task resume and receipt-backed…