Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wrg32786/aigent-osnpx agentmods add skills/wrg32786/aigent-os/meta-improveWrote 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/wrg32786/aigent-os/meta-improve)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/meta-improve"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/meta-improve.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 49 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00027 | $0.00483 |
| Opus 5 | $0.00014 | $0.00242 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
meta-improve 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 7d 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.
What it actually says
Constrained self-improvement
The public verb is /meta-improve-vault.
Input and gate
Select only from canonical vault/memory/DREAM_LOG.md: an exact candidate
whose status is approved and whose approval was written by
/dream --set-status from a direct operator decision. proposed is not
approval.
Read only the exact evidence references named by that approved candidate from
vault/memory/runtime/LESSONS.jsonl and
vault/memory/runtime/NIGHTLY_CAPTURE_CANDIDATES.jsonl. Those products provide
traceability; they never provide approval by themselves.
Before Build:
node daemons/nightly-contracts.mjs meta --root <aigent-root> \
--candidate <candidate-id>
Require META_GATE PASS. It checks the canonical block for exact approved
status and non-placeholder operator evidence. This is the executable
nightly-contracts.mjs meta gate.
Build
For one approved candidate:
- Re-read its evidence, proposed change, mutation proof, and scope.
- Use repository isolation where normal policy requires it.
- Apply the smallest change satisfying the proposal.
- Run the real red-before and green-after proof plus relevant system checks.
- Produce a review artifact with exact diff, commands, exits, residual risks, and rollback.
- Surface
accept / reject / reviseto the operator.
Never merge, push, deploy, broaden scope, modify an operator gate, approve
another candidate, or infer approval. A failed proof asks the Dream writer to
set the candidate blocked.
Status ownership
This skill never edits Dream directly. The Dream writer owns:
- direct operator approval:
proposed -> approved; - verified build failure:
approved -> blocked; - direct rejection:
approved -> rejected; - independently verified merge:
approved -> merged.
The complete flow is:
propose -> operator gate -> build -> independent review -> operator outcome
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.
- 7d ago First seen · 65 lines · 27 tokens per session scan A c124ef535f74
meta-improve is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 483 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 2026-09-01.
Other skills, from other repositories
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
article
Write a publication-ready article in one of three angles - a trending long-form piece, a watched-repo thesis, or a project-through-a-lens essay. Optional Replicate hero image with --visual.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
fleet-control
Operate managed Aeon instances from memory/instances.json - health-check, dispatch, and status snapshots (control), plus a fleet scorecard of runs, tokens, cost, and reliability (scorecard).
github-trending
Curated trending across GitHub repos and the Hugging Face Hub (models, datasets, spaces) - filtered, clustered, and labeled by momentum with a one-line why-notable per pick.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.