Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/gsaranti/pantheon/metis-reconcile)<a href="https://agentmods.dev/skills/gsaranti/pantheon/metis-reconcile"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-reconcile/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/gsaranti/pantheon/metis-reconcile"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-reconcile.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 | $0.00032 | $0.00835 |
| Opus 5 | $0.00016 | $0.00417 |
| Sonnet 5 | $0.00006 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
metis-reconcile 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/metis-reconcile
Read everything under docs/. Produce four reconcile artifacts: .metis/SYNTHESIS.md, .metis/INDEX.md, .metis/CONTRADICTIONS.md, .metis/QUESTIONS.md.
Preflight
Run references/reconcile-preflight.sh before reading. It exits non-zero if docs/ is missing (surface the error and stop). Otherwise it reports STATUS (fresh / rereconcile), SIZE_CLASS (small / medium / large), and counts for the corpus and any prior items.
On SIZE_CLASS=large, apply the slicing guidance in references/reconciling-docs.md.
Load
- The source docs under
docs/. - On
rereconcile, the prior.metis/CONTRADICTIONS.mdand.metis/QUESTIONS.md. Re-reconcile preserves prior items and re-checks them against the current corpus (perreferences/reconciling-docs.md) rather than starting over.
Do not load
.metis/RESOLVED.md..metis/BUILD.md.
Read first
references/reconciling-docs.md — read before drafting any of the output artifacts.
Write scope
Four files in .metis/, all pre-created as stubs by the preflight so they exist before any write and Edit can target them on the first run.
Cadence — write across the read, not in a terminal batch. The artifacts take shape as you read: INDEX.md and SYNTHESIS.md grow as concepts and gaps surface, and CONTRADICTIONS.md / QUESTIONS.md accrue as items are found. Writing incrementally keeps reruns cheap — Edit against a file that already exists rather than a full Write re-emitting unchanged content — which is what the rest of this section assumes.
Write each artifact in its own step, and Read a file before the first Write/Edit that touches it — Claude Code refuses to overwrite a file it has not read this session, so a read-then-write keeps every write valid on the first attempt and isolates any failure to a single file.
.metis/SYNTHESIS.md— fullWrite, regenerated from the current corpus rather than patched..metis/INDEX.md— built during the first pass. OnSTATUS=fresh, grow it from the stub; onSTATUS=rereconcile, preferEdit: add, update, or remove individual entries surgically and leave unchanged entries in place..metis/CONTRADICTIONS.md— sameEdit-preferred discipline on rereconcile. Preserve items markedstale. Re-emitting unchanged items asWriteoutput is the cost we're avoiding..metis/QUESTIONS.md— same treatment asCONTRADICTIONS.md.
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 First seen · 57 lines · 32 tokens per session scan A bebbe1c77896
metis-reconcile is a skill published in the GitHub repository gsaranti/pantheon (3 stars, last pushed 20d ago), licensed MIT. It adds 32 tokens to every session and 835 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…