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 skills/ingo-eichhorst/irrlicht/ir-execnpx skills add ingo-eichhorst/Irrlicht --skill ir-execgit clone --depth 1 https://github.com/ingo-eichhorst/IrrlichtWrote 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/skills/ingo-eichhorst/irrlicht/ir-exec)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-exec"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-exec.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 | $0.00158 | $0.19986 |
| Opus 5 | $0.00079 | $0.09993 |
| Sonnet 5 | $0.00032 | $0.03997 |
| Haiku 4.5 | $0.00016 | $0.01999 |
Grade C, and why
ir:exec 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
second gate: don't refuse, don't stop the turn, don't ask for confirmation. The How it starts
The opening of the file, as written. The whole thing — 1,218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute a GitHub Issue, End to End
Take an issue from a number to a review-clean, landed PR:
/ir:exec [mode] <N>
Four modes share one flow; mode defaults to auto when omitted.
ir:exec always works in its own worktree (Phase 1), so there's no separate
"runs in a worktree" naming convention to invoke — the mode is just an
argument.
/ir:exec [mode] <N>
→ not-already-claimed? → worktree → investigate → (auto resolves to plan or full here)
→ plan: HTML + ⛔ approval, or full: inline summary → assign issue
→ implement → verify → commit
→ PR → review subagent (effort scaled to diff) → fix → /simplify (or inline) → recommendation [plan / full stop here]
→ land: confirm mergeable → squash-merge → remove worktree [close]
Modes
| Mode | Invocation | Gate? | Stops after |
|---|---|---|---|
auto (default) |
/ir:exec <N> or /ir:exec auto <N> |
Decided from the issue's /ir:triage signals — see Auto mode below |
Whatever the resolved mode (plan or full) stops after |
plan |
/ir:exec plan <N> |
Yes — render HTML plan, end turn, wait for explicit approval | Phase 6 (hand-back), once approved |
full |
/ir:exec full <N> |
No — skip the wait | Phase 6 (hand-back) |
close |
/ir:exec close [N] (or replying "merge" to Phase 6) |
n/a | Phase 7 (land) |
full still follows every other rule in this skill — worktree isolation, one
branch/PR per issue, AGENTS.md conventions — only the approval wait and the
HTML plan artifact are dropped.
Auto mode
auto never invents a new strategy — it picks between plan and full using
signals /ir:triage already computes, then proceeds exactly as that mode
would from there on.
auto issues no gh reads of its own: the readiness label and triage comment
are read in Phase 2 step 3, which every mode runs. auto only interprets
what that read already returned.
Read the tiers in order and stop at the first that yields a value — the richer signal wins, and the legacy tier is explicit rather than an accident of a loose regex:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 1,218 lines · 158 tokens per session scan C 39290a53d530
ir:exec is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (96 stars, last pushed yesterday), licensed MIT. It adds 158 tokens to every session and 19,986 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
project-init
Scaffold an unconfigured directory into a configured pi project. Interactive, profile-driven: previews the planned writes, then writes AGENTS.md, .pi/settings.json and prompt files — optionally also a knowledge base, an openspec/ scaffold, and user-global /.pi/agent/settings.json. Use on a bare directory, or when the…