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-discover.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-discover)<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-discover"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-discover/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-discover"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-discover.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 | $0.09291 | $0.09291 |
| Opus 5.5 | $0.03716 | $0.03716 |
| Sonnet 5.5 | $0.01858 | $0.01858 |
| Haiku 4.5 | $0.00929 | $0.00929 |
Grade C, and why
idd-skill idd-discover.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-discover.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 — 735 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDD — Discover Phase (A0-T–A4)
Read this file to select the next issue, including explicit targets, roadmap-audit handoff, and A4.5/Claim routing.
With helpers, run first from docs/idd-helper-scripts.md for
A0-C/A0-O/A3/A3.5/A4/A4.5; tables win if absent/disagrees.
discover-viability-gate/discover-shared-file-overlap: --issue/--issues.
Abort conditions: A0-T, A1 (orphan-first/roadmap scope only —
see A0), A3 (default; see decision tree).
Early stop condition: A0-T, A1.5, A4, or A4.5 (no claim made — see
below).
Authoring label guard
Use issueAuthoring.authoringLabelName (default: status:authoring) and
issueAuthoring.authoringStaleAge (default: PT4H). The label marks held
drafts and suppresses claims, so skip labeled issues. Unlabeled issues follow
anchor logs; incomplete generations block. Only exact
anchor/set/session release-complete gates release/guard; an absent label is
not proof; release clears it.
The
portable owner resolver
defines these owner-protocol terms for every helper profile. For
instructions-only, never infer membership from the label.
A0-T, A0-O, and A3 must treat a matching label as not startable. A0-T
(step 1) stops before claim; A0-O and A3 filter the issue out. For each
skipped issue, fetch the latest matching labeled timeline event. If the
label age exceeds authoringStaleAge, emit:
Warning: Issue #N has carried the authoring label for {duration}; the authoring session may be stalled.
If the timestamp is unavailable, still skip the issue and report that the stale-authoring age could not be checked.
A0-C — Draft-carrier entry
Before A0-T, A0 and any claim, run the profile-selected
discover-orphan-filter --draft-carriers (not under instructions-only).
If it exits non-zero or prints no draftCarriers field, stop the run,
report the exit status and stderr, and claim nothing. List
draftCarriers.held carriers whose stale is true in the run report;
releasing them is 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.
- 2d ago Changed · +2 lines · +23 tokens per session 36455ec3a18c
- 5d ago Changed · +9 lines · +89 tokens per session dcaf087ae599
- 6d ago Changed · +10 lines · +184 tokens per session 792299d1a0ed
- 7d ago Changed · +1 lines · +6 tokens per session ba495d5c8989
- 8d ago Changed · -4 lines · +5 tokens per session 5f2a1d193e6a
- 10d ago Changed · -1 lines · -2 tokens per session 67a5e4133fe8
- 12d ago Changed · +3 tokens per session 641fe2715b74
- 20d ago Changed · -1 lines · +5 tokens per session e352cb2a7760
- 24d ago Changed · +7 tokens per session 1199344e73aa
- 25d ago First seen · 719 lines · 8,971 tokens per session scan C 3efb680adac9
idd-skill idd-discover.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed today), licensed MIT. It adds 9,291 tokens to every session, about $0.0372 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.