Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.agents/skills/orch/SKILL.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/orch)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/orch"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/orch/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/vanillagreencom/kendex/orch"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/orch.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 | $0.00023 | $0.07015 |
| Opus 5.5 | $0.00009 | $0.02806 |
| Sonnet 5.5 | $0.00005 | $0.01403 |
| Haiku 4.5 | $0.00002 | $0.00702 |
Grade C, and why
orch scanned grade C with 1 finding 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:project-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
A worktree created as an orch lane follows the Refresh ownership and committed outputs heading in these orch Project Instructions, including its local-fleet case when no refresh workflow exists. Respect the lane refresh restriction. A lane explicitly launched to refresh runs kendex refresh or kendex apply only with --lane-refresh, as its brief permits. An ordinary worktree follows its own project resolution and retains actionable drift repair details. Use the explicit lane record to distinguish them.
The hosted overseer coordinates from the control VM. Run item implementation, builds, installation, tests and validation in an owned lane. Where the fleet runs a control-host guard, that guard reads control-host-toolchain.conf. It blocks cargo, npm, pnpm, yarn, npx, tsc, vitest, biome, eslint and next; tools/guard, dev-validate-run and post-merge; and commands from DEV_VALIDATE_CMD or ORCH_POST_MERGE_CMD. This block includes post-merge --refresh-only. The absence of a guard does not permit item builds, installation, tests or validation on the control host. For refresh ownership and synchronization after merge, follow the Refresh ownership and committed outputs heading in these orch Project Instructions. Do not run a blocked command through a wrapper.
Refresh ownership and committed outputs
Use the repository-declared owner for kendex refresh outputs. Kendex uses its lock-record Actions workflow and rolling kendex/lock pull request. Consumers with automatic refresh use their kendex-refresh Actions workflow and rolling kendex/refresh pull request. When no refresh workflow exists and the fleet is local, the overseer owns refresh in the base checkout. Keep the local-fleet full post-merge route. This local owner is not a hosted control VM. Confirm the execution owner and its output paths before adoption. A hosted consumer without a refresh workflow must confirm an authorized owner outside the control VM. The hosted overseer runs sync-base to receive committed outputs after they merge. It does not run post-merge or post-merge --refresh-only on the control VM. Post-merge does not refresh or verify a base checkout that holds .github/workflows/kendex-refresh.yml; in other base checkouts, it reports refresh changes and keeps them. Preserve unrelated tracked and untracked work. Keep each refresh workflow under its existing owner.
What ships with it
60 files 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.
- docs/hosted-oversight.html 31 KB
- docs/orch.css 3.8 KB
- kendex.settings.toml.example 24 KB
- README.md 18 KB
- references/agent-transcripts.md 2.4 KB
- references/artifact-checks.md 5.0 KB
- references/codex-runtime.md 21 KB
- references/communication-modes.md 27 KB
- references/control-host-toolchain.conf 882 B
- references/copilot-head-notices.md 11 KB
- references/copilot-runtime.md 22 KB
- references/copilot-wait.md 1.6 KB
- references/design-review.md 6.9 KB
- references/gates.md 10 KB
- references/heartbeat-audit.md 7.6 KB
- references/job-units.md 9.7 KB
- references/lane-directive.md 38 KB
- references/lane-reach.md 21 KB
- references/merge-attempt.md 4.3 KB
- references/narrow-change.conf 10 KB
- references/oversee-events.md 87 KB
- references/oversee-lanes.md 12 KB
- references/overseer-session-events.md 12 KB
- references/peer-mail.md 8.2 KB
- references/pi-runtime.md 8.6 KB
- references/secret-value.ere 1.5 KB
- references/security-alerts.md 5.4 KB
- references/skill-rules.md 42 KB
- references/thread-read.md 3.2 KB
- references/waiter-launch.md 4.3 KB
- references/watch-delivery.md 15 KB
- schemas/copilot-credits.md 4.4 KB
- schemas/dev-return.md 16 KB
- schemas/dev-round.md 11 KB
- schemas/lane-host.md 53 KB
- schemas/overseer-host.md 9.4 KB
- schemas/workflow-state.md 89 KB
- scripts/approval-wait 77 KB
- scripts/base-freshness 4.0 KB
- scripts/ci-wait 52 KB
- scripts/claude-model-classes/.claude-plugin/plugin.json 216 B
- scripts/claude-model-classes/hooks/hooks.json 35 B
- scripts/claude-model-classes/hooks/register.js 7.8 KB runs code
- scripts/container-close 24 KB
- scripts/copilot-lane-context/extension.mjs 10 KB runs code
- scripts/copilot-lane-context/model-list.mjs 3.5 KB runs code
- scripts/copilot-statusline 3.7 KB
- scripts/copilot-wait 5.6 KB
- scripts/dev-artifact-check 56 KB
- scripts/dev-return-write 54 KB
- scripts/dev-round-write 23 KB
- scripts/dev-validate-run 85 KB
- scripts/git-context 6.9 KB
- scripts/item-tier 8.2 KB
- scripts/lane-close 93 KB
- scripts/lane-host 6.6 KB
- scripts/lane-host-ssh 60 KB
- scripts/lane-mail 276 B
- scripts/lane-marker 12 KB
- scripts/lanes 268 KB
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.
- 5d ago Changed 01cf30199376
- 8d ago Changed e4bea105b556
- 9d ago Changed 898573e450f1
- 10d ago Changed 715610818c84
- 11d ago Changed 702e69177397
- 12d ago Changed 8a538dce7488
- 13d ago Changed · +6 lines a3ab257775b0
- 14d ago Changed 34a980166f70
- 16d ago Changed 9f46704cbca5
- 17d ago First seen · 209 lines · 23 tokens per session scan C 867d3fd9d16b
orch is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 7,015 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
linear-tracker
Resolve project-local issue tracker routing and publish Linear issues safely. Use before creating Linear issues, PRDs, phase breakdown issues, or when deciding whether Linear/GitHub/local docs is the configured tracker. Enforces capability ≠ routing: Linear requires project-local policy, team association, auth, and…
github
Use when interacting with GitHub repositories, issues, pull requests or Actions through the gh CLI.