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-discussgit 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-discuss)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/hex-discuss"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-discuss/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-discuss"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/hex-discuss.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 | $0.00086 | $0.05773 |
| Opus 5.5 | $0.00034 | $0.02309 |
| Sonnet 5.5 | $0.00017 | $0.01155 |
| Haiku 4.5 | $0.00009 | $0.00577 |
Grade A, and why
hex-discuss 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hex-discuss — Pre-Plan Discussion Mode
hex-discuss talks a problem through before anything is decided: it elaborates
the ask, argues with the answers, checks disputed facts in the background while
the conversation keeps going, and keeps what was settled in a discussion
artifact. It builds nothing and writes no plan, ADR, or spec — the run ends at
a drain, the explicit handoff that closes the discussion and names the
command to run next.
It is a hex skill, not a fifth orchestrator: no classify.md, no
overlays.md, no tier-*.md, and no tier vocabulary of its own. The
dispatcher/tier-file split is vacuous here, not deviated from — there are no
tier files to dispatch to.
Shared contracts:
protocol.md ·
workers.md ·
models.md ·
memory.md.
If hex-core is not installed: grim add ghcr.io/michael-herwig/arcana/hex-core:latest.
Argument syntax
/hex-discuss <topic | path | slug>. Free text becomes intake slot 1 and is
never re-asked; a path into the resolved discussions home, or the slug of
an existing artifact, resumes that artifact
(The discussion artifact).
Entry and exit
Entered only by explicit user invocation or by this skill's own description
match on a user's discuss request — never self-triggered from another hex
skill's flow (the hex-init precedent). The frontmatter leaves
claude.disable-model-invocation unset: the description match is the entry
path. Entry then resolves the discussion's home and either opens the existing
artifact or writes the stub
(The discussion artifact). Exit is only an explicit
drain (Handoff) or an explicit user abort. There is no third exit:
no turn budget, no idle timeout, no "this looks finished" self-exit. An abort
leaves State: parked, re-enterable later under the same slug.
What ships with it
2 files 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 6e6fd9034432
- 21d ago Changed · +6 lines 0e085ed8aa41
- 1mo ago First seen · 410 lines · 86 tokens per session scan A e1b0e36ac846
hex-discuss is a skill published in the GitHub repository grimoire-rs/grimoire (14 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 5,773 once invoked, about $0.0003 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
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.
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.
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.
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.