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 gsaranti/pantheon --skill metis-session-startgit clone --depth 1 https://github.com/gsaranti/pantheonWrote 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-session-start)<a href="https://agentmods.dev/skills/gsaranti/pantheon/metis-session-start"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-session-start.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 5.1 | $0.00016 | $0.00664 |
| Opus 5 | $0.00008 | $0.00332 |
| Sonnet 5 | $0.00003 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
metis-session-start 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 8d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/metis-session-start
Read the minimum set of files that orients the agent to the project's current state.
Preconditions
.metis/ must exist. If it does not, stop and point at /metis-init.
Partial state inside .metis/ (missing or incomplete files) surfaces as an Anomaly in the Return rather than a hard error.
Load
In this order:
.metis/CURRENT.md— the previous session's handoff, including the active-task pointer. The primary rehydration source..metis/SYNTHESIS.md— what's being built, when it exists. Loaded once at session start so the rest of the session's work can lean on it without re-reading..metis/INDEX.md— the concept → source-doc map, when it exists..metis/BUILD.md— the build backlog, when it exists. Confirms the active item and shows what remains.
Do not load
.metis/CONTRADICTIONS.md,.metis/QUESTIONS.md,.metis/RESOLVED.md— reconcile/walk artifacts. Loaded on demand by the skills that need them, not at session start.docs/— source corpus. Loaded on demand by skills that turn on specific passages.
Write scope
None.
Return
- Active task — the active item: the one named by
CURRENT.mdActive task when it points at a liveBUILD.mdentry, otherwise the first To build item as next-up (the pointer lags until/metis-session-endfirst sets it — e.g. right after/metis-build-spec). Include backlog progress fromBUILD.md(e.g. "2 built, 9 to build"). If the backlog isn't built yet, say so. - What happened last session — one paragraph from
CURRENT.mdWhat happened. IfCURRENT.mdis missing or empty, say so directly. - In flight — what's being worked on right now, from
CURRENT.mdCurrent state — including, when the active item spans multiple tasks, where the item stands and what its next task is. If nothing is in flight, say so. - Open questions — the list from
CURRENT.mdOpen questions. Surfaced as items the user may want to address. - Where to start — directly from
CURRENT.mdWhere to start. Do not rewrite — pass it through. - Anomalies — anything unexpected: missing
CURRENT.md(suggest/metis-init), an Active task pointer that names an entry absent fromBUILD.md,CURRENT.mdreferencing files that don't exist on disk,.metis/BUILD.mdorSYNTHESIS.mdmentioned by the handoff but absent. Surface rather than absorb.
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.
- 8d ago First seen · 47 lines · 16 tokens per session scan A 1e99a7c8b800
metis-session-start is a skill published in the GitHub repository gsaranti/pantheon (3 stars, last pushed 16d ago), licensed MIT. It adds 16 tokens to every session and 664 once invoked, about $0.0001 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: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:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
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…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:my-context-graph
Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.