Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/kurone-kito/idd-skill/idd-workgit 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-work)<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-work"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-work.svg" alt="Measured on agentmods" 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 | $0.05072 | $0.05072 |
| Opus 5 | $0.02536 | $0.02536 |
| Sonnet 5 | $0.01014 | $0.01014 |
| Haiku 4.5 | $0.00507 | $0.00507 |
Grade C, and why
idd-skill idd-work.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 4d 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-work.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 — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDD — Work and Self-Review Phase (B + C)
Read this file after a successful claim. It covers worktree creation (B1), planning (B2), implementation (B3), and the self-review loop (C).
B1 — Create worktree (with branch)
Before creating, check for local conflicts in this order:
-
Ensure the local
mainbranch is up to date and has no local commits. Run this from the primary worktree while onmain:git fetch origin main git log origin/main..main --onelineIf the second command outputs any lines, local
mainhas unpushed commits — stop and report, do not force-resetmain. Otherwise, fast-forward to origin:git merge --ff-only origin/mainAfter this
mainfast-forward, do not change the primary worktree's HEAD offmainfor any reason during B1 — see Anti-patterns below for the forbidden commands and the allowed HEAD-preserving exceptions (read-only inspection, and the HEAD-preserving branch/worktree commands used by Steps 2-3 below and by Worktree creation). -
Run
git worktree list— if a worktree for the branch already exists, inspect and acquire its worktree-local claim lock before reusing or removing it (same helper commands as there); do not rungit worktree removewhile the lock check is still a collision — resolve it via the Claim-state rule inidd-claim.instructions.md, and only remove the path once the current claim is authorized to take it over. Reusing it keeps the acquired lock; removing it means recreating the path and re-acquiring the lock before any install or other mutation (removal must precede branch deletion — git blocks deleting a checked-out branch).
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.
- 4d ago First seen · 439 lines · 5,072 tokens per session scan C b6a13bf5373e
idd-skill idd-work.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed 4d ago), licensed MIT. It adds 5,072 tokens to every session, about $0.0254 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
GRC-Mapping-Analyst GEMINI.md
Gemini CLI instructions for austinsonger/GRC-Mapping-Analyst, covering strm mapping — gemini cli context, purpose of this repository, when to perform strm mapping, working directory and saving completed mappings.
GRC-Mapping-Analyst AGENTS.md
AGENTS.md instructions for austinsonger/GRC-Mapping-Analyst, covering strm mapping — agent instructions, repository purpose, project constraints (apply to all work), activating the strm skill (codex) and strm methodology quick reference.
GRC-Mapping-Analyst copilot-instructions.md
Copilot instructions for austinsonger/GRC-Mapping-Analyst, covering github copilot instructions — strm mapping repository, core concepts, output files, file naming convention and strength score formula.
AgentSkills copilot-instructions.md
Copilot instructions for jeremylongworth-source/AgentSkills: Use installed AgentSkills when a task matches a skill description. Read the matching SKILL.md before applying a specialist workflow.
supergraph AGENTS.md
Instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
idd-framework AGENTS.md
AGENTS.md instructions for GrillerGeek/idd-framework, covering agents.md — intent-driven development framework, what is idd?, artifact hierarchy, output directories and artifact schemas.