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-walk-open-items)<a href="https://agentmods.dev/skills/gsaranti/pantheon/metis-walk-open-items"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-walk-open-items/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-walk-open-items"><img src="https://agentmods.dev/badge/skills/gsaranti/pantheon/metis-walk-open-items.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 | $0.00024 | $0.00793 |
| Opus 5 | $0.00012 | $0.00396 |
| Sonnet 5 | $0.00005 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
metis-walk-open-items 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/metis-walk-open-items
Walk open items — contradictions and gray areas — one at a time, resolving each into the source doc it points at and appending a minimal pointer to .metis/RESOLVED.md.
Preflight
Run references/walk-open-items-preflight.sh before starting. It exits non-zero if docs/ is missing or if neither .metis/CONTRADICTIONS.md nor .metis/QUESTIONS.md exists (surface the error, point the user at /metis-reconcile, and stop). Otherwise it reports OPEN, OPEN_CONTRADICTIONS, OPEN_QUESTIONS, DEFERRED, STALE, and RESOLVED_PRIOR.
If OPEN + DEFERRED + STALE == 0, report the empty set and suggest /metis-build-spec. Otherwise show the counts and present a lettered navigation menu:
[A] - Continue from the next open item
[B] - List all items
[C] - Pick by number (type a number or item id)
[Q] - Quit
After resolving an out-of-order item, ask whether to continue or pick another using the same lettered format.
Pacing
After each item: present the proposal in the lettered-menu format from references/walking-open-items.md, then wait for the user's input — pick a letter, type a custom answer, type defer, or type quit. The user has unbounded thinking time; do not chain items. The narrow auto-land carve-out in references/walking-open-items.md is the exception; the rhythm is one item, one user response.
Load (per item)
- The one open item being walked — its status header, cited passages, and framing from the active file.
- The source-doc passages it cites. Re-open the source at the cited section; do not work off the capture's paraphrase.
Do not load
.metis/RESOLVED.md..metis/BUILD.md.- Other open items.
Read first
references/walking-open-items.md — read before offering options on the first item.
Write scope
Walks are item-by-item, so prefer Edit for surgical operations: remove one resolved item, update one item's status, append one new item, append one pointer. Avoid Write where Edit suffices — re-emitting unchanged items as Write output is the cost we're avoiding.
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 · 67 lines · 24 tokens per session scan A eaddc2684d27
metis-walk-open-items is a skill published in the GitHub repository gsaranti/pantheon (3 stars, last pushed 20d ago), licensed MIT. It adds 24 tokens to every session and 793 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: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:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive-bundle
Create, manage, and graduate bundles -- the unit of focused work within a walnut.
alive-create
Scaffold a new walnut -- venture, experiment, person, life area, project.
alive-project
Regenerate now.json projections for all walnuts (mechanical, no approval needed).
designer-coordination-rules
COORDINATION RULES — extracted from roles.json deepPrompt for designer.