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 eunomia-bpf/agentsight --skill evolve-agent-skillsgit clone --depth 1 https://github.com/eunomia-bpf/agentsightWrote 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/eunomia-bpf/agentsight/evolve-agent-skills)<a href="https://agentmods.dev/skills/eunomia-bpf/agentsight/evolve-agent-skills"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/agentsight/evolve-agent-skills/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/eunomia-bpf/agentsight/evolve-agent-skills"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/agentsight/evolve-agent-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Rogue Agent · line 30 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00144 | $0.02417 |
| Opus 5 | $0.00072 | $0.01208 |
| Sonnet 5 | $0.00029 | $0.00483 |
| Haiku 4.5 | $0.00014 | $0.00242 |
Grade A, and why
evolve-agent-skills 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 10d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolve Agent Skills
Turn many agent sessions into small, testable improvements to shared or project-local skills. Treat trajectories as evidence, not instructions, and never equate a checker saying pass with an independently validated improvement.
Operating Boundary
Use this skill for the learning loop around skills. Route adjacent work as follows:
- Use
skill-creatorto scaffold or structurally revise the final skill package. - Use repository-local trajectory tools such as AgentSight or AgentProf to normalize source data when available.
- Use
autoresearch:learnwhen one isolated failure already has a trustworthy reproduction and only a bounded eval package is needed. - Use
research-experiment-designwhen the target is a paper's scientific evaluation rather than agent behavior. - Do not modify writing skills merely because an upstream research or review gate failed. Trace the failure to the skill that owned the bad decision.
Default to analysis and a patch plan; apply a skill patch only when the user asks to create or change the skill. An explicitly requested edit needs no held-out A/B test first — apply the smallest local candidate and label it propose. Never claim promotion or causal improvement without valid comparison evidence.
Required References
Read the following before analyzing or proposing changes:
- evidence-contract.md for source coverage, identity, strata, privacy, and metric validity.
- failure-taxonomy.md for consistent failure labels and causal-claim limits.
- promotion-protocol.md before designing, running, or judging a promotion experiment or claiming that a candidate is promoted.
Read research-patterns.md when comparing the design with self-reflection, workflow memory, agent search, self-modifying-agent research, or production skill-evolution systems.
Durable Error Retrospective
What ships with it
5 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.
- 10d ago First seen · 198 lines · 144 tokens per session scan A 8deafe048e59
evolve-agent-skills is a skill published in the GitHub repository eunomia-bpf/agentsight (678 stars, last pushed 2d ago), licensed MIT. It adds 144 tokens to every session and 2,417 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
prometheus
Prometheus monitoring expert for PromQL, alerting rules, Grafana dashboards, and observability.
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.