idd-skill: Instructions file for GitHub Copilot

.github/instructions/idd-resume-stall.instructions.md

idd-skill idd-resume-stall.instructions.md is an instructions file for GitHub Copilot from kurone-kito/idd-skill. It costs 2,546 tokens per session, scanned C, original, MIT.

A recovery procedure for resuming an IDD task after a coding session stops making progress or becomes rate-limited. It uses current server-side issue, pull-request, claim, branch, and test information.

In plain words
What is it for?
Use it to collect the required activity and test signals, identify stalled non-owned claims, and decide whether to resume, wait, or stop.
Why use it?
It helps determine whether a previous agent is still working, whether its claim is stale, and whether taking over the task is safe.

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 →

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-resume-stall.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-resume-stall.instructions.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-resume-stall"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-resume-stall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,546 This file is loaded in full into every session.
When invoked 2,546 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 $0.02546 $0.02546
Opus 5 $0.01273 $0.01273
Sonnet 5 $0.00509 $0.00509
Haiku 4.5 $0.00255 $0.00255

Measured 9d ago against content hash 7baff14cf76e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

idd-skill idd-resume-stall.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 9d 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-resume-stall.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-resume-stall.instructions.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IDD — Resume Stalled-Session Recovery

Use this file when Resume sees signs of a progress-stalled or rate-limited session and needs a dedicated, safety-first decision path. This path relies only on externally observable state. It never depends on the prior session posting a graceful shutdown.

This file applies only to unattended stale-takeover evidence for a non-owned claim. Human-gated forced handoff is a separate recovery path and is routed from idd-resume.instructions.md before this file runs.

Read idd-overview-core.instructions.md and idd-resume.instructions.md first.

Inputs to collect

Before deciding, gather:

  1. Active claim details from trusted marker actors only: {claim-id}, {agent-id}, latest valid claimed-by created_at, and branch.
  2. Current issue and PR activity timestamps (comments, review-thread updates, review submissions).
  3. PR head SHA and latest completed CI timestamp for that head (or none), plus current CI run/check states (queued / in_progress / terminal) and their start/update timestamps.
  4. PR head update timestamp (when the current head entered the PR), or remote branch tip SHA and update time when no PR exists.
  5. Latest trusted review watermark and baseline marker timestamps for the same active claim (if present).
  6. A server-anchored now for the S2/S4 quiet-window bound — see "Deriving a server-anchored now" below.

Use GitHub server timestamps only.

Deriving a server-anchored now

The S2/S4 quiet-window bound [now - 30 min, now] must share the same clock as the activity timestamps gathered above (GitHub server time), not the executor's local clock — the local clock can be skewed ahead of or behind the server, which can push genuinely recent activity outside the window and make quiet_window_met spuriously true.

Read the full file on GitHub · 228 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. 9d ago First seen · 228 lines · 2,546 tokens per session scan C 7baff14cf76e

Subscribe to this mod's changes

idd-skill idd-resume-stall.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed yesterday), licensed MIT. It adds 2,546 tokens to every session, about $0.0127 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

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

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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens