Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkitWrote 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/rjmurillo/ai-agents/skillopt)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/skillopt"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/skillopt/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/rjmurillo/ai-agents/skillopt"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/skillopt.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 | $0.00103 | $0.03745 |
| Opus 5.5 | $0.00041 | $0.01498 |
| Sonnet 5.5 | $0.00021 | $0.00749 |
| Haiku 4.5 | $0.00010 | $0.00375 |
Grade A, and why
skillopt 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 3d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillOpt
A candidate lands only when it adds at least one held-out pass and loses none. No scored eval set means no gate, and no gate means no edit.
SkillOpt treats a skill document as the trainable state of a frozen model. You run rollouts and reflect on failures. The bundled scripts decide whether an edit may exist: the edit budget, the patch applier, the protected-section guard, the rejected-edit buffer, and the acceptance gate are deterministic. Do not edit the target by hand. Route every edit through the scripts so the gate is real. Method: Yang et al., arXiv:2605.23904. The paper's reported gains are its claims; this skill does not reproduce them.
Triggers
| Phrase | Action |
|---|---|
optimize this skill |
Run the Process below against a scored eval set |
make this skill better |
Same, after the Preconditions pass |
compress these skills safely |
Declare a resource task up front, then gate |
tune this prompt against an eval |
Same loop with a prompt as the target |
| A skill keeps failing the same way | Mine sessions, confirm the defect, then gate |
Boundaries
| Need | Owner |
|---|---|
| Create a skill, find one, or route a request to one | skillforge |
| Decide skill vs passive context, or compress markdown with no eval | context-optimizer |
| Measured improvement of an existing skill, agent file, or prompt | this skill |
Held-out optimization of agents, rules, and hooks inside the rjmurillo/ai-agents checkout |
optimize-artifact.py in that repository's eval tooling (not shipped) |
Preconditions (hard stop if unmet)
- Target artifact. A
SKILL.md, agent file, or prompt. - Scored eval set. A nonempty held-out
selsplit with per-task pass or fail verifiers (references/eval-set-format.md). Without one, stop and say so.scoreandpair-gateexit 2 on a missing or empty split. - Canonical owner. Name the versioned source, its generated mirrors, and the live install path before any candidate runs. A file in an eval workspace is not deployed behavior.
What ships with it
15 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.
- references/cross-machine-mining.md 3.9 KB
- references/eval-set-format.md 5.9 KB
- references/example-candidate-results.json 145 B
- references/example-eval.json 2.2 KB
- references/example-incumbent-results.json 148 B
- references/mechanism.md 2.2 KB
- references/slow-section-convention.md 1.6 KB
- scripts/_mine_handoff.py 5.4 KB runs code
- scripts/_mine_records.py 10 KB runs code
- scripts/_mine_sources.py 3.0 KB runs code
- scripts/_skillopt_buffer.py 3.0 KB runs code
- scripts/_skillopt_gates.py 9.6 KB runs code
- scripts/_skillopt_patching.py 6.8 KB runs code
- scripts/mine_sessions.py 8.3 KB runs code
- scripts/skillopt.py 11 KB runs code
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.
- 3d ago First seen · 304 lines · 103 tokens per session scan A 8f425bab9a5a
skillopt is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 3,745 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.
Other skills, from other repositories
parity-guard-test-pattern
When checking that all callers of a contract implement it correctly, you get false positives from wrapper delegators.
phoenix-review
Review completed work against the Intent Contract's acceptance criteria using objective evidence, not opinion — re-run every check, confirm no regressions, inspect the tamper-evident trace, and surface only real issues (bugs, unmet criteria, regressions). Use before shipping, after a feature is built, or when the user…
loop-verifier
Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
053-design-simple-rules
Use when Java design, refactoring, or implementation tradeoffs should be evaluated with Kent Beck's simple design rules, including passes the tests, reveals intention, has no duplication, and has the fewest elements. This should trigger for requests such as Apply simple design rules; Review this design with Beck's…
Pair Programming
AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…