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-finalizegit 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-finalize)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/hex-finalize"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-finalize/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-finalize"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-finalize.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 | $0.00049 | $0.05687 |
| Opus 5.5 | $0.00020 | $0.02275 |
| Sonnet 5.5 | $0.00010 | $0.01137 |
| Haiku 4.5 | $0.00005 | $0.00569 |
Grade A, and why
hex-finalize 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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hex-finalize — The Finalize Phase
hex-finalize takes a review-approved feature branch from the work is right
to this is ready to merge: it verifies the branch, recomposes it into a
commit series the project's own rules would accept, and — after exactly one
approval — force-pushes it and readies its pull request. The merge is never hex's:
the run ends at a handoff naming it as the human's step, emitting no command.
It is a hex skill, not a fifth orchestrator: no tier vocabulary of its own. The flow is one fixed sequence whose universals do not scale with blast radius, so there is nothing for a tier to select.
Entry is explicit invocation only, never a description match — the
invocation is the grant for the action class, so it must originate with a
human, or a session acting on a human-pasted C-805a grant
(finalize.md § Consent model).
The frontmatter says so to clients that read it; the rule binds in clients
that drop those keys. Exit is the handoff block, or a pre-flight halt.
This is the one hex command that writes to a remote. Every rule it obeys
is defined once in finalize.md and
linked from here; this file carries the flow.
Shared contracts:
protocol.md ·
workers.md ·
models.md ·
memory.md ·
finalize.md.
If hex-core is not installed: grim add ghcr.io/michael-herwig/arcana/hex-core:latest.
Argument syntax
/hex-finalize [<target-branch>]. The argument names the branch to land
onto, never the branch being finalized — that is always the one checked out
in the primary checkout.
The target resolves from authoritative sources only, in precedence order:
- the explicit argument;
- the open pull request's base field;
- the discovered trunk.
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 · +11 lines f1c3b803af7e
- 21d ago Changed · +15 lines d8326685cb3d
- 1mo ago First seen · 410 lines · 49 tokens per session scan A fd885db1de92
hex-finalize is a skill published in the GitHub repository grimoire-rs/grimoire (14 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 5,687 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 2026-09-08.
Other skills, from other repositories
inbox-triage
Daily GitHub notification inbox triage - surfaces aging vuln PR replies, security advisories, review requests, and mentions that need action.
install-skill
Install a community skill pack into this fork from a GitHub repo and ship it as an auto-merged PR.
repo-stats-autoupdate
Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, review-based validation, and communication standards.
git-commit
Safely create a git commit by validating repository state, staging intended changes, scanning for secrets/conflicts, generating a Conventional Commits message (repository convention first, else an English Angular default) from the staged diff, and committing without amend.