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.
curl -O https://raw.githubusercontent.com/kurone-kito/idd-skill/main/.github/instructions/idd-claim.instructions.mdgit clone --depth 1 https://github.com/kurone-kito/idd-skillWrote 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/instructions/kurone-kito/idd-skill/idd-claim)<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-claim"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-claim/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/instructions/kurone-kito/idd-skill/idd-claim"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-claim.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 | $0.08826 | $0.08826 |
| Opus 5.5 | $0.03530 | $0.03530 |
| Sonnet 5.5 | $0.01765 | $0.01765 |
| Haiku 4.5 | $0.00883 | $0.00883 |
Grade C, and why
idd-skill idd-claim.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 3d 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-claim.instructions.md Generated by sync-docs. Edit the source above, then run `node scripts/sync-docs.mjs --apply`; do not edit this file. --> How it starts
The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDD — Claim Phase (A5)
Read this file after idd-suitability.instructions.md (A4.5) passes for
the selected issue — whether selected via A4 or verified through an
explicit issue target (A0-T) — or after a successful re-claim decision
in the resume phase. It covers the five pre-checks, claim execution, and
claim verification.
Canonical A5(a) path (helper-first)
When helper runtime is enabled, use the profile-selected claim approval helper as the canonical A5(a) evidence collector.
# source repo / vendored-node
node scripts/claim-approval-gate.mjs --issue <issue-number>
# package-manager / ephemeral-npx / user-global
<profile-selected-claim-approval-command> --issue <issue-number>
Resolve <profile-selected-claim-approval-command> from
docs/idd-helper-scripts.md; do not hardcode node scripts/... for
non-vendored profiles.
Contract: docs/idd-helper-scripts.md#claim-approval-evidence (required
fields: approved, reason, gateEnabled,
policy.maintainerApprovalActorPolicy, policy.approvalSignals,
checks).
If the helper exits non-zero, returns invalid or incomplete JSON, or conflicts with live approval state, ignore it and use the written A5(a) path below. If fallback still cannot prove safe approval, treat approval as missing.
Context-pressure stop
Fresh candidate: before claim, if context pressure prevents completing Claim through F4, report for handoff; stop; do not claim. Recovery unchanged. Make no claim-stage event/marker, branch/worktree, or issue-state change. (#3144; preventive)
Pre-checks (all five must pass)
Re-fetch the issue before checks. A5 is target-local except child release:
follow its persisted anchor's paginated log for exact generation; related
claims do not block. Owner protocol:
docs/idd-autonomy-contract.md#portable-authoring-owner-protocol.
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.
- 3d ago Changed · +4 lines · +61 tokens per session 27cd767b4e57
- 4d ago Changed · -1 lines · -58 tokens per session 80648072d510
- 7d ago Changed · -10 lines · -95 tokens per session d439687f7401
- 8d ago Changed · +47 lines · +798 tokens per session 77c574704cdc
- 9d ago Changed · +1 lines · +32 tokens per session 72a4c5d45af9
- 10d ago Changed · -52 lines · -634 tokens per session fc5fc789333f
- 11d ago Changed · +1 lines · +11 tokens per session 1dd11569bdbe
- 12d ago Changed · +9 tokens per session e983ac2051fc
- 20d ago Changed · +1 lines · +16 tokens per session d96edb42c310
- 24d ago First seen · 724 lines · 8,686 tokens per session scan C c80d36b032ee
idd-skill idd-claim.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed today), licensed MIT. It adds 8,826 tokens to every session, about $0.0353 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 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).
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.
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).
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.
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).
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.