idd-skill: Instructions file for GitHub Copilot

.github/instructions/idd-merge.instructions.md

idd-skill idd-merge.instructions.md is an instructions file for GitHub Copilot from kurone-kito/idd-skill. It costs 6,714 tokens per session, scanned C, original, MIT.

A set of instructions for merging a completed pull request in an IDD workflow, including cleanup and starting the next task.

In plain words
What is it for?
Use it to verify merge ownership and policy, merge an approved pull request when allowed, clean up afterward, and return to task discovery.
Why use it?
It prevents a coding agent from merging changes when its ownership claim is missing or when the repository requires human approval or another merge agent.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/audit-pr-cleanup.mjs --pr <pr-number> --dry-run --format table.

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/idd-merge.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 idd-merge.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-merge.svg)](https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-merge)
Your own site
<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-merge"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-merge.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,714 This file is loaded in full into every session.
When invoked 6,714 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 $0.06714 $0.06714
Opus 5 $0.03357 $0.03357
Sonnet 5 $0.01343 $0.01343
Haiku 4.5 $0.00671 $0.00671

Measured 2d ago against content hash 386eda4e9dc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

idd-skill idd-merge.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 2d 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/idd-merge.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/idd-merge.instructions.md · 511 lines

How it starts

The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IDD — Merge Execution Phase (F3–F5)

Read only after idd-merge-handoff.instructions.md routes the current claim to the autonomous merge path. Covers executing the merge (F3), cleanup (F4), and looping back to discover (F5).

The final merge-gate timing defaults are named in IDD policy constants; the merge logic itself stays here.

Before any mutating action in F3, apply the shared claim revalidation gate.

F3 — Merge

  1. Confirm the claim is still yours: the active claim must still use your current {claim-id}. If it is missing, released, or held by a different {claim-id} (even under the same agent ID), the claim was lost — report and stop.
  2. Defensive route check: re-read the repository's recorded merge policy (missing → treat as human_merge, the distributed default). Then apply:
    • fully_autonomous_merge: continue.
    • separate_merge_agent: continue only when repository documentation explicitly records the current session as the designated merge-capable actor and the documented resume condition is satisfied; otherwise route to idd-merge-handoff.instructions.md and stop.
    • human_merge or unknown policy: route to idd-merge-handoff.instructions.md and stop.
  3. Immediately before executing the merge command, do one final live fetch using the exact same activity-universe scope as E1 Step 1 (all review threads, review bodies, and regular PR comments, excluding trusted agent operational marker comments), and compare it against the F2 snapshot carried forward from idd-pre-merge.instructions.md. When helper runtime is enabled, prefer the documented merge-gate helper reference in docs/idd-helper-scripts.md to collect the snapshot tuple and broader pre-merge-readiness JSON report. Both helpers remain read-only evidence collectors only: if execution fails, output is invalid JSON, required sections are missing, or live GitHub state disagrees with it, discard helper output and run the live fetch directly — the written gate rules remain canonical. Return to E1 if any of F2's Review-currency return-to-E1 triggers apply, substituting the carried F2-snapshot fields for F2's own stored watermark fields: {f2-head-SHA} for {head-SHA}, {f2-max-activity-updatedAt} for {max-activity-updatedAt}, {f2-total-item-count} for {total-item-count}, and {f2-latest-ci-completed-at} for {latest-ci-completed-at} — this final fetch is the live side of each comparison, exactly as F2's own live snapshot was.

Read the full file on GitHub · 511 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. 2d ago Changed · +55 lines · +757 tokens per session 386eda4e9dc3
  2. 8d ago First seen · 456 lines · 5,957 tokens per session scan C cc4f8339a028

Subscribe to this mod's changes

idd-skill idd-merge.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed today), licensed MIT. It adds 6,714 tokens to every session, about $0.0336 per session on Opus 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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 · 7,296 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens