idd-skill: Instructions file for GitHub Copilot

.github/instructions/claim-orchestrator.instructions.md

idd-skill claim-orchestrator.instructions.md is an instructions file for GitHub Copilot from kurone-kito/idd-skill. It costs 1,143 tokens per session, scanned C, original, MIT.

Instructions for an issue-driven development workflow in which an orchestrator assigns a verified work claim to another agent. A claim records who owns a task and which activation identity the worker must keep.

In plain words
What is it for?
Use them when coordinating subagents that implement repository changes through tracked issues and claim tokens.
Why use it?
Delegating work without clear ownership can cause duplicate work or conflicting changes. These rules preserve the original claim and require the worker to recheck it before proceeding.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions subagents.

This is kurone-kito/idd-skill's own configuration. It tells GitHub Copilot how to work on idd-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything idd-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kurone-kito/idd-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kurone-kito/idd-skill/main/.github/instructions/claim-orchestrator.instructions.md
Clone the repo
git clone --depth 1 https://github.com/kurone-kito/idd-skill

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for idd-skill claim-orchestrator.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/claim-orchestrator/github.svg)](https://agentmods.dev/instructions/kurone-kito/idd-skill/claim-orchestrator)
Your own site
<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/claim-orchestrator"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/claim-orchestrator/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.

agentmods 80×15 button for idd-skill claim-orchestrator.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/claim-orchestrator"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/claim-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,143 This file is loaded in full into every session.
When invoked 1,143 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01143 $0.01143
Opus 5.5 $0.00457 $0.00457
Sonnet 5.5 $0.00229 $0.00229
Haiku 4.5 $0.00114 $0.00114

Measured 6d ago against content hash 688600f06837, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

idd-skill claim-orchestrator.instructions.md 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 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.

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.

<!-- idd-generated-from: idd-template/.github/instructions/claim-orchestrator.instructions.md Generated by sync-docs. Edit the source above, then run `node scripts/sync-docs.mjs --apply`; do not edit this file. -->
.github/instructions/claim-orchestrator.instructions.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IDD — Claim Phase: Orchestrator delegation

Read this file only when this session is an orchestrator that delegates a verified claim to a subagent worker. idd-claim.instructions.md points here from its Orchestrator delegation section.

An orchestrating session that has posted and verified a claim's {agent-id} / {claim-id} pair may delegate it verbatim to an isolated subagent worker in the delegation brief. The worker adopts both fields verbatim as its own claim token — mirroring the adopt-verbatim rule in idd-claim.instructions.md — instead of minting a fresh claim or being treated as claim-less; see the ownership-proof exception in Claim-state parsing. No separate claimed-by post is required for the delegation itself.

Carry the nonce, don't mint one — and still revalidate it. The brief must also carry the orchestrator's current activation nonce verbatim; minting a new nonce for the same {claim-id} creates the exact two-nonce collision that step 4 of Claim verification exists to catch, flagging legitimate delegation as a second activation. The worker still performs the Claim revalidation gate's nonce check (idd-overview-core.instructions.md) using the carried value: before each mutation, recompute the nonce winner for the {claim-id} and confirm it still equals the carried nonce. A different winner (e.g. a later forced-handoff collision the orchestrator never saw) means the worker is no longer the winning activation — treat that the same as any other lost claim.

State the worker role explicitly when the delegate inherits full context. Some delegation mechanisms give the worker the orchestrator's own complete conversation context instead of a clean slate limited to the brief. There, the worker can carry over the orchestrator's own framing — mistaking itself for the session that launched several workers and is waiting on their replies — instead of recognizing the brief reassigns it to a single-issue worker role. The delegation brief must state explicitly that the delegate is the sole worker for the named issue, that no peer workers exist for it to coordinate with or wait on, and that it must perform the implementation work itself rather than re-delegate or wait for a reply (#2179). Use a non-context-inheriting mechanism whenever the tool offers one — this is a strong preference, not a suggestion; a context-inheriting mechanism (e.g. forking the orchestrator's own conversation) is a fallback only when no non-context-inheriting option exists. See docs/idd-workflow.md's Orchestrator fan-out variant.

Known limitation. Neither this wording nor an added negative instruction reliably stops a context-inheriting delegate from misreading itself as a sub-orchestrator waiting on a nonexistent sub-worker (#2802) — an accepted residual risk of the fallback path; see docs/idd-design-rationale.md for the field evidence.

Restate the CI/advisory-wait wake-up discipline. Carry — verbatim or by reference — both mitigations from idd-ci.instructions.md's Wake-up discipline: the topology-safety condition (#2210; also in docs/idd-workflow.md's Orchestrator fan-out variant) and the execution-timeout override for a heavy or long-running local command (#2933).

Restate the scratchpad file-naming requirement. See docs/idd-workflow.md's Orchestrator fan-out variant: each worker must prefix scratchpad filenames with the issue number, or use an issue-numbered subdirectory.

Read the full file on GitHub · 91 lines

Changes

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.

  1. 6d ago Changed · +14 lines · +189 tokens per session 688600f06837
  2. 10d ago First seen · 77 lines · 954 tokens per session scan C 856283383e56

Subscribe to this mod's changes

idd-skill claim-orchestrator.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed today), licensed MIT. It adds 1,143 tokens to every session, about $0.0046 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 2026-10-11.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,384 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens