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-suitability.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-suitability)<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-suitability"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-suitability/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-suitability"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-suitability.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 | $0.04932 | $0.04932 |
| Opus 5.5 | $0.01973 | $0.01973 |
| Sonnet 5.5 | $0.00986 | $0.00986 |
| Haiku 4.5 | $0.00493 | $0.00493 |
Grade C, and why
idd-skill idd-suitability.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 today.
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-suitability.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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDD — Pre-Claim Suitability Triage (A4.5)
Read this file after A4 picks a candidate (A4 Step 2), or after A0-T
verifies an explicit issue target, and before idd-claim.instructions.md.
Position: After A4 (viability), before A5 (claim)
Scope: Explicit-target, roadmap, and orphan-first candidates
Purpose: Filter incoherent, unsafe, duplicated, or out-of-scope
issues, independent of the current run's context. Where A4 asks "can we
do this NOW?", A4.5 asks "SHOULD we do this at all?"
Relationship to the autopilot-suitability score
The numeric <!-- idd-skill-autopilot-suitability: N -->
footer is a discovery-time ranking/routing hint consumed in
idd-discover.instructions.md (floor: the effective policy's
autopilotSuitability.floor, default 3; see also
docs/policy-constants.md). It is not one of the seven checks: A4.5
PASS/FAIL is decided solely by the qualitative checks, never by the
score. A low or missing score never fails this gate; a high score never
bypasses it.
When helper support is enabled, use helper scripts from
docs/idd-helper-scripts.md first for A4.5 evidence.
Written checks and decision flow remain authoritative when helper output
is missing or disagrees.
Issue-author approval is a separate pre-claim gate. Candidates that fail
the repository's issue-author approval evaluation are routed by
idd-discover.instructions.md and re-checked in
idd-claim.instructions.md; they are not rejected through A4.5.
Seven Suitability Checks
For the candidate picked in A4 Step 2 (or the explicit target verified by A0-T), evaluate the following checks in order. Stop and fail on the first check that is not satisfied.
Check 1: Repository Fit
Does the issue describe work scoped to this repository?
- Pass: Work is entirely within this repository's scope; no external system coordination needed
- Fail: Issue crosses repository boundaries, requires external system access, or is out-of-scope for this repository
- A negative regression fixture or expected-rejection example is descriptive
context, not a live prerequisite, only when an explicit, positively framed
fixture/rejection cue precedes the external-access phrase in the same
Markdown paragraph or list item. On a list marker line, the cue and phrase
must remain in the same sentence; a separate sentence is part of the same
context only when it is a correctly indented loose-list continuation
paragraph whose cue text also identifies the external/access context. A
heading at the list item's indentation ends that context. Inline-code terms
remain scannable when they occur in a live prerequisite, while fixture cues
inside inline code, strikethrough, and inline-code-only examples are
ignored. A separate live prerequisite still fails this check, while
unrelated or negated cues (including
non-/not-prefixed variants), a cue after the access phrase, a cue in another paragraph, and ambiguous wording remain fail-closed. This boundary follows the observed false positive in issue #3522. - Outcome on fail:
out-of-scope
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.
- today Changed · +1 lines · +11 tokens per session 4108af9c03c0
- 10d ago Changed · -2 tokens per session a207724e682e
- 11d ago Changed · -1 lines · +4 tokens per session 3f8cacf49add
- 14d ago Changed · +1 lines · +16 tokens per session a7e35a66f6c1
- 24d ago Changed · +20 lines · +308 tokens per session deaa07bd7742
- 1mo ago Changed · +4 lines · +43 tokens per session 638604c982ae
- 1mo ago Changed · +46 lines · +647 tokens per session 2aa55368b2ee
- 1mo ago Changed · +6 lines · +71 tokens per session 0699cc43b4c5
- 1mo ago Changed · +9 lines · +124 tokens per session 20837df7f7d8
- 1mo ago First seen · 333 lines · 3,710 tokens per session scan C ecec932e2b2a
idd-skill idd-suitability.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed today), licensed MIT. It adds 4,932 tokens to every session, about $0.0197 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.