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 skills add grimoire-rs/grimoire --skill hex-loopgit clone --depth 1 https://github.com/grimoire-rs/grimoireWrote 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/grimoire-rs/grimoire/hex-loop)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/hex-loop"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-loop/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/skills/grimoire-rs/grimoire/hex-loop"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-loop.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 | $0.00053 | $0.07909 |
| Opus 5.5 | $0.00021 | $0.03164 |
| Sonnet 5.5 | $0.00011 | $0.01582 |
| Haiku 4.5 | $0.00005 | $0.00791 |
Grade A, and why
hex-loop scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hex-loop — Goal File and Loop Prompt
hex-loop turns a settled goal into two things: one goal file, the binding
per-run contract (definition of done, autonomy, issue resolution, loop shape,
rules, emphasis, context, source), and one paste-ready prompt of at most
4,000 characters that drives an unattended meta-orchestrator run of the hex
modes against it. It starts, pushes and commits nothing — pasting is the only
confirmation, which is why it carries no approval gate of its own
(protocol.md § The meta-plan approval gate
lists it as exempt).
It is a hex skill, not a fifth orchestrator: no tier vocabulary. It spawns nothing; the flow is one fixed sequence with nothing for a tier to select.
Entry is explicit invocation only, never a description match. Its output is a paste for a human, so a model-invoked run would only write a stray goal file. The frontmatter says so to clients that read it; this rule binds in clients that drop the key.
Shared contracts:
protocol.md ·
memory.md ·
finalize.md ·
archive.md.
Goal-file template: goal.md — the
section menu, the criterion line format and evidence forms, the full doubt
protocol, and the branch, commit and tick policy live there, never here.
If hex-core is not installed: grim add ghcr.io/michael-herwig/arcana/hex-core:latest.
Argument syntax
/hex-loop <source> [extras…]. <source> is one of:
- a path to a discussion, ADR, plan, spec, or goal file — repo-relative, absolute, or in a sibling repo; read as a read-only pointer, never edited;
#N,PR N, orissue N;- a GitHub PR or issue URL.
A path's kind is read from its first # heading — # Discussion:,
# ADR:, # Plan:, # Spec: (the hex-init templates), or # Retro: (a
retro report) — else from the hex.md › Pointers home it sits in. It is a
goal file only when it carries the goal template's Written: <date> by /hex-loop header line, and then it must also carry the template's seven
fixed ## headings (Errors (e)). A path of none of these kinds
is Errors (f).
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.
- 12d ago Changed · +3 lines 8cdcc3e76018
- 21d ago First seen · 449 lines · 53 tokens per session scan A d40b8b7dc446
hex-loop is a skill published in the GitHub repository grimoire-rs/grimoire (14 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 7,909 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other skills, from other repositories
vuln-scanner
Audit trending repos for real security vulnerabilities and disclose responsibly - scan and route findings (PVR / dependency PR), re-submit queued advisories, and send armed email disclosures.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
autoresearch
Evolve a skill by generating variations, evaluating them, and updating the best version.