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-review-fix.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-review-fix)<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-review-fix"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-review-fix/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-review-fix"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-review-fix.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 | $0.05633 | $0.05633 |
| Opus 5 | $0.02816 | $0.02816 |
| Sonnet 5 | $0.01127 | $0.01127 |
| Haiku 4.5 | $0.00563 | $0.00563 |
Grade C, and why
idd-skill idd-review-fix.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-review-fix.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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDD — Review Fix Phase (E9–E15)
Read this file after idd-review-triage.instructions.md (E8) finds
Accepted PATH A items. Covers implementing fixes, validating, pushing,
replying to reviewers, and waiting for CI — including E14's GitHub
Copilot advisory-review step, which follows even when another local
agent drives the workflow, since it depends on GitHub review state, not
the local CLI. E14's timing defaults are named in
IDD policy constants; refer there for
values, but keep the phase logic here unchanged.
Apply the shared claim revalidation gate before E9, the E12 push, and each E13/E14/E15 GitHub side effect (reply, resolve, reviewer request, hold comment, or digest update).
E9 — Fix accepted issues
Fix all Accepted PATH A items from ReviewItems_snapshot. Run fix-validate. Commit fixes atomically — one logical change per commit.
Within-round batching. All of this round's Accepted PATH A fixes travel as their own atomic commits, but push together in a single push at E12 — do not push after each individual fix. See E12 for the push step and the bounded cross-round allowance for comments arriving before that push.
These fix-side rules complement the accept-side "Verify before accept"
rule in idd-review-triage.instructions.md (E5); each cuts the
advisory-review round count:
- Fix the whole class, not just the flagged line. Sweep the current diff (and adjacent sections) and fix every instance of a systemic finding in one commit — this converges faster than waiting for each instance to be re-flagged.
- Verify any claim a fix adds. Check any new precision (a name, value, path, or described behavior) against the actual implementation before committing.
- Already fixed via batching. A PATH A item Accepted (E4/E5) may already be folded into a prior E12 push — confirm the commit addresses it and let E13 cite that SHA, without duplicating the fix.
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 · +80 lines · +1,160 tokens per session 0d63ea1850bd
- 8d ago First seen · 364 lines · 4,473 tokens per session scan C f835ad24e471
idd-skill idd-review-fix.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed today), licensed MIT. It adds 5,633 tokens to every session, about $0.0282 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.
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.
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.
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).
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).
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.
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.