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 agentmods add skills/gsaranti/pantheon/metis-implement-tasknpx skills add gsaranti/pantheon --skill metis-implement-taskgit 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-implement-task)<a href="https://agentmods.dev/skills/gsaranti/pantheon/metis-implement-task"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-implement-task.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 | $0.00018 | $0.01120 |
| Opus 5 | $0.00009 | $0.00560 |
| Sonnet 5 | $0.00004 | $0.00224 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
metis-implement-task 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/metis-implement-task
Implement the task described by the plan in context, and close with a scope report.
Arguments
- Trailing prompt — optional. Augments the plan in context per the command-prompts convention. If no plan is in context, the prompt serves as the description and the agent treats it as a single-step brief.
Context expected
A plan or description present in conversation context. It can come from any of:
- A recent
/metis-plan-taskinvocation in this session — structured plan in chat history. - An informal plan or description discussed with the user in this session before invoking this skill — chat history, however it got there.
.metis/CURRENT.mdloaded by/metis-session-start— a prior session captured the plan there.- The trailing prompt to this command, when it's specific enough to serve as the brief.
If none of these are present, ask the user before proceeding. Implementing against an unstated brief is the silent-drift failure mode this skill exists to avoid.
The plan may cover one task toward a larger BUILD.md item, not the whole item. Implement the planned task and let the scope report name what remains of the item; don't widen to finish the entire item in one pass — that's the scope creep the redline below guards against.
Load (task-specific)
- The code the task is changing, on demand as implementation proceeds. Confined to surfaces named in the plan's expected file changes — widening goes in the scope report.
- Source-doc passages the plan cites or the description points at, at the named paths.
Do not load
.metis/CONTRADICTIONS.md,.metis/QUESTIONS.md,.metis/RESOLVED.md.- Other session state beyond the plan and what the plan points at.
Read first
references/honest-scope-reporting.md — read before composing the closing scope report.
Write scope
- Code and test files. Confined to surfaces named in the plan's expected file changes. Widening — touching files the plan did not name — goes in the scope report.
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.
- 4d ago First seen · 81 lines · 18 tokens per session scan A 8269d2291cca
metis-implement-task is a skill published in the GitHub repository gsaranti/pantheon (3 stars, last pushed 12d ago), licensed MIT. It adds 18 tokens to every session and 1,120 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: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: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…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.