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-overview-appendix.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-overview-appendix)<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-overview-appendix"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-overview-appendix/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-overview-appendix"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-overview-appendix.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 | $0.02049 | $0.02049 |
| Opus 5.5 | $0.00820 | $0.00820 |
| Sonnet 5.5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade C, and why
idd-skill idd-overview-appendix.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-overview-appendix.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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDD — Reference and Implementation Appendix
This appendix contains reference content, implementation details, and
maintainer guidance for the IDD workflow. The core runtime definitions
are in idd-overview-core.instructions.md.
Policy Constants
The distributed claim, advisory, CI, and critique-loop defaults are
named in docs/policy-constants.md. Read it before changing a timing
or loop constant; record local deviations in onboarding or
repository docs.
Live status digest
The optional live status digest is a human-facing issue or PR comment
whose first line is <!-- idd-live-status: current -->. It is never an
authority for IDD state — decide from trusted operational markers and
GitHub state. If multiple marked digests exist, preserve them, report
the URLs, and treat none as authoritative unattended. See
docs/idd-comment-minimization.md for the contract and
node scripts/live-status-digest.mjs, an optional helper (use the
profile-selected form from docs/idd-helper-scripts.md).
Treat each digest create or edit as a GitHub side effect under the claim
revalidation gate (idd-overview-core.instructions.md), with fields
from the revalidated claim; set Authoritative by to the evidence.
A PR digest edit is still PR activity: do not edit it between a valid
E1 review watermark and an intended F3 merge (it would perturb
review-currency). Edit it only when leaving merge intent (returning to
E1, routing F3 to F1/D4 as blocked, or a hold/stop), after F3 has
merged, or while F2 is blocked only on secondaryQuietWindow (no
longer perturbs it); the F3 awaiting-reviewer restart-F2 path skips
edits too.
Abort
On abort, re-validate ownership first. If the active claim still uses
your current {claim-id}, update the digest before posting
unclaimed-by so it shows Phase: aborted/released, the planned
release in Next action, and the verified claim plus abort reason in
Authoritative by; then post an unclaimed-by comment for that same
{claim-id}. If the
active claim no longer uses your {claim-id}, do not update the digest
or post a release comment.
Open PR and remote branch left by a stale or
unclaimed state are inheritable by the next agent (see
idd-resume.instructions.md).
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.
- 2d ago Changed · -2 lines · -39 tokens per session d2c8ca498404
- 5d ago Changed · -1 lines · -20 tokens per session f18277063d3a
- 10d ago Changed · -10 lines · -118 tokens per session fddc7646a70e
- 14d ago Changed · +1 lines · +16 tokens per session 68699a9e9088
- 27d ago Changed · +3 tokens per session 73d6659f7136
- 1mo ago Changed · +3 lines · -13 tokens per session c7a3e2580b63
- 1mo ago Changed · -1 lines · -14 tokens per session a7c26887aff6
- 1mo ago Changed · +34 lines · +435 tokens per session 1a76289c66d9
- 1mo ago Changed · +10 lines · +111 tokens per session ef8cdc90fa2f
- 1mo ago First seen · 156 lines · 1,688 tokens per session scan C ca2bd3703e4f
idd-skill idd-overview-appendix.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed today), licensed MIT. It adds 2,049 tokens to every session, about $0.0082 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.