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-pr-submitgit 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-pr-submit)<a href="https://agentmods.dev/instructions/kurone-kito/idd-skill/idd-pr-submit"><img src="https://agentmods.dev/badge/instructions/kurone-kito/idd-skill/idd-pr-submit.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 | $0.04743 | $0.04743 |
| Opus 5 | $0.02371 | $0.02371 |
| Sonnet 5 | $0.00949 | $0.00949 |
| Haiku 4.5 | $0.00474 | $0.00474 |
Grade C, and why
idd-skill idd-pr-submit.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 5d 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-pr-submit.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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IDD — PR Submit Phase (D)
Read this file after the self-review loop passes. It covers pre-publication main sync, claim verification, tests, pushing, PR creation, and waiting for CI.
Before the D1 sync and D2 push, apply the shared claim revalidation gate.
D1 — Sync main before first push
If the branch has not been pushed yet, sync it onto main before the
first push — the routine pre-publication history cleanup step. First run
git fetch origin main, then check whether the branch is already
current with origin/main: if git merge-base HEAD origin/main equals
origin/main (behind-count 0), the branch already contains every commit
on main, so the rebase would be a pure no-op. Skip the rebase entirely
and proceed to D2 — D1's pre-publication synchronization goal is already
met. In a sibling-worktree setup a no-op git rebase origin/main can still
detach HEAD at the upstream tip without replaying the local commit, and
re-running that no-op rebase re-detaches every time, so the bounded
recovery below cannot converge for the no-op case; skipping it is the clean
exit.
Otherwise the branch is behind origin/main: rebase it onto main
(git rebase origin/main), then apply the post-rebase verification and
bounded recovery below.
After the first D-phase push, do not reuse D1 as the normal
synchronization path. Later branch updates should return through the
E-phase review loop and, by default, merge main into the published PR
branch so the synchronization diff is reviewable.
This D-phase file records the publication boundary only: post-push
synchronization itself runs through idd-review-triage.instructions.md's
E-phase branch-sync check (Esync), which uses the
branch-conflict-state helper when helper runtime is enabled (a
gh pr view fallback otherwise), and idd-resume.instructions.md
already routes a content-conflicting branch there on restart.
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.
- 5d ago First seen · 411 lines · 4,743 tokens per session scan C 6aabe1e13e77
idd-skill idd-pr-submit.instructions.md is an instructions file published in the GitHub repository kurone-kito/idd-skill (11 stars, last pushed 5d ago), licensed MIT. It adds 4,743 tokens to every session, about $0.0237 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
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.
dining-places-skill CLAUDE.md
Claude Code instructions for ddalgrande/dining-places-skill, a project described as: Agent Skill that turns your Google Maps saved places into a personal dining knowledge base and gives taste-matched eating-out advice.
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).
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.
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.
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.