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 metraton/gaia --skill gaia-compactgit clone --depth 1 https://github.com/metraton/gaiaWrote 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/metraton/gaia/gaia-compact)<a href="https://agentmods.dev/skills/metraton/gaia/gaia-compact"><img src="https://agentmods.dev/badge/skills/metraton/gaia/gaia-compact/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/metraton/gaia/gaia-compact"><img src="https://agentmods.dev/badge/skills/metraton/gaia/gaia-compact.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 | $0.00031 | $0.00693 |
| Opus 5 | $0.00015 | $0.00347 |
| Sonnet 5 | $0.00006 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
gaia-compact 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gaia Compact
Gaia Compact preserves the small amount of transient context needed to resume work after compaction. Durable decisions and work belong in memory, briefs, plans, tasks, or project context; compact references those objects instead of duplicating their bodies.
Process
- Collect user extras. Preserve any specific item the user names.
- Classify what would be lost, by which door you came in. After a
session-reflection, every decision, learning, and pending already has a home, soUNSAVED TRANSIENT CONTEXTis empty by construction: anything you are tempted to put there names an item the reflection did not finish, and it belongs back in that table rather than in a summary that expires. Arriving standalone with unsaved decisions, learnings, milestones, or Gaia improvements, offer thesession-reflection→memoryflow first; if the user insists on compacting now, preserve those items explicitly under that field, labeled as not durable rather than pretending permanence. - Preflight continuity. Resolve or clearly retain approvals in flight, unpersisted brief/plan changes, verification evidence, and requested git actions. Compaction does not make them durable.
- Build the handoff. Preserve only:
- active objective;
- exact resume point;
- durable references (slugs, brief/plan/task IDs), never their bodies;
- unsaved transient facts;
- blockers and approvals;
- active files needed to resume;
- user-provided preservation instructions.
- Invoke
/compactwith that handoff -- the orchestrator's own action; this skill cannot invoke it.
Preservation prompt
Preserve continuity for the next turn:
- ACTIVE OBJECTIVE: <goal>
- RESUME POINT: <exact next action>
- DURABLE REFERENCES: <memory slugs and brief/plan/task IDs; no copied bodies>
- UNSAVED TRANSIENT CONTEXT: <facts that exist only in this conversation>
- BLOCKERS / APPROVALS: <current state>
- ACTIVE FILES: <only files needed to resume>
- USER EXTRAS: <request-specific instructions, if any>
Compress tool output and intermediate reasoning. Do not duplicate durable
memory or structured work; retain identifiers and the next decision.
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.
- 9d ago First seen · 71 lines · 31 tokens per session scan A 561e0498215b
gaia-compact is a skill published in the GitHub repository metraton/gaia (3 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 693 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
review-team
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
ultra
Fans the work out as a fleet of parallel Grok and Codex agents billed to their own subscriptions, then synthesizes one result. The peer engine equivalent of ultracode, adding intensity without spending Claude quota on the fleet. Use it for genuinely broad goals, not only explicit asks for intensity.
grok-prompting
Brief writing guidance for composing self contained Grok briefs for coding, review, diagnosis, and second opinion tasks.
smoke
Runs a three probe live smoke wave after a plugin update and reports gate chain health before real work rides it.
codex-result-handling
Internal contract for returning Codex companion output without alteration.
shipwrights-loop
Drive multiple Jira tickets sequentially through the /shipwrights-epic pipeline. Auto-picks the next ticket, watches the PR until merged, transitions Jira to shipped, repeats. Resumable across Claude Code sessions via .shipwrights/loop-state.json. Invoked as /shipwrights-loop [N] | --status | --abort.