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 Evolvlabsai/Exolvra-Genesis --skill statusgit clone --depth 1 https://github.com/Evolvlabsai/Exolvra-GenesisWrote 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/evolvlabsai/exolvra-genesis/status)<a href="https://agentmods.dev/skills/evolvlabsai/exolvra-genesis/status"><img src="https://agentmods.dev/badge/skills/evolvlabsai/exolvra-genesis/status/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/evolvlabsai/exolvra-genesis/status"><img src="https://agentmods.dev/badge/skills/evolvlabsai/exolvra-genesis/status.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 | $0.00048 | $0.01060 |
| Opus 5.5 | $0.00019 | $0.00424 |
| Sonnet 5.5 | $0.00010 | $0.00212 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
status 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 1mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain STATUS.md
This repo keeps a STATUS.md at the root. It is read by an external chief-of-staff agent that briefs the founder, so its shape is fixed and its contents must be true. You maintain it; you do not redesign it.
When to update
Update STATUS.md in the same commit or PR as the work, at every one of these points:
- End of every session, before your final message, even if the session changed nothing (bump
updatedand say so under Latest). - After any merge to the default branch.
- After a release, deploy, or version bump.
- When a blocker appears or clears.
- When a decision is made that changes scope, stack, or priority.
If you cannot write the file (read-only session, no repo access), say so explicitly in your final message with the lines that should have changed.
Rules
- Facts only. Every line must be verifiable from git history, CI, an issue tracker, or a file in the repo. Write what happened, not what is planned to happen, except under Next, and label plans there as plans.
- Derive from the repo, not from memory. Before writing, run
git log --since=<previous updated date> --oneline, check CI status, and diff the working tree. Do not carry forward a line you cannot re-verify; delete it or move it to Done with its date. - Dates on everything. ISO dates (
2026-09-14). No "recently", "soon", "this week". - Keep headings exactly as in the template, in the same order, even when a section is empty (write
None.). The reader parses by heading. - Never delete history. Done items stay under Done for 30 days, then roll into one line under History.
- Short. Each bullet one line, under 140 characters. Whole file under 120 lines. Trim Done and History before Blocked or Next.
- Health is computed, not felt:
green= CI passing on default branch and nothing under Blocked;amber= CI passing but something under Blocked, or CI unknown;red= CI failing on default branch or a blocker older than 7 days. - Blocked means "cannot proceed without something outside this repo": a decision, a credential, a third-party, a person. Everything else is Next.
- Needs-founder lines are questions or approvals only, phrased so a yes/no or short answer resolves them. Include what you will do on each answer.
- Do not put secrets, tokens, customer names, or private URLs in this file. It leaves the repo.
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.
- 1mo ago First seen · 91 lines · 48 tokens per session scan A 293c39c08698
status is a skill published in the GitHub repository Evolvlabsai/Exolvra-Genesis (1 stars, last pushed 24d ago), licensed MIT. It adds 48 tokens to every session and 1,060 once invoked, about $0.0002 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 2026-09-19.
Other skills, from other repositories
lifecycle
Complete milestone lifecycle -- audit, archive, deferred items, and next version preparation.
verify
Verify phase deliverables match acceptance criteria.
status
Show project progress, current phase, and next actions.
settings
View and modify Megazord project configuration.
go
Execute the current phase plan (subagent or Agent Teams mode).
plan
Plan a phase into executable tasks with dependencies and waves.