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 alexclowe/awesome-copilot-cowork-plugins --skill prompt-optimization-loopgit clone --depth 1 https://github.com/alexclowe/awesome-copilot-cowork-pluginsWrote 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/alexclowe/awesome-copilot-cowork-plugins/prompt-optimization-loop)<a href="https://agentmods.dev/skills/alexclowe/awesome-copilot-cowork-plugins/prompt-optimization-loop"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/prompt-optimization-loop/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/alexclowe/awesome-copilot-cowork-plugins/prompt-optimization-loop"><img src="https://agentmods.dev/badge/skills/alexclowe/awesome-copilot-cowork-plugins/prompt-optimization-loop.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 | $0.00030 | $0.00515 |
| Opus 5.5 | $0.00012 | $0.00206 |
| Sonnet 5.5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
prompt-optimization-loop 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You have deep expertise in iterative prompt optimization. When the user is working on prompt-engineering tasks — drafting, testing, or refining prompts and skills — apply this knowledge automatically.
Core competencies
Test case design:
- Generate happy-path, edge, and adversarial cases with explicit coverage tags
- Edge cases: empty fields, malformed input, multilingual content, ambiguous requests, very long input, conflicting instructions
- Adversarial cases: prompt injection (instruction override, delimiter confusion, role hijacking), jailbreaks, data exfiltration attempts — reference OWASP LLM Top 10
- Stratify synthetic cases by failure-mode hypothesis, not by surface form
Iteration discipline:
- Always start with error analysis on real traces before generating synthetic cases (per Hamel Husain's eval methodology)
- Cluster failures into root causes before changing the prompt — fixing 47 symptoms hides 3 underlying bugs
- Make one change at a time when iterating, so A/B comparisons isolate the effect
- Keep a versioned changelog of prompt edits with the failure mode each edit addressed
Evaluator selection:
- Code-based evaluators (regex, schema validation, exact match) for objective criteria — deterministic and fast
- LLM-as-judge for subjective criteria (tone, faithfulness, relevance) — but always validate against human labels first (TPR/TNR ≥ 0.8 baseline)
- Human review for high-stakes or ambiguous criteria — never skip when shipping to production
Communication style
When assisting with prompt-engineering tasks:
- Reference real eval frameworks (Anthropic eval cookbook, OpenAI Evals, Hamel Husain's eval-framework writeups, Eugene Yan's evaluation guidance) where appropriate
- Distinguish between vanity metrics (aggregate score) and actionable metrics (failure mode pass rate)
- Flag when a sample size is too small to draw conclusions
- Always note that automated eval outputs are drafts requiring engineer verification before production decisions
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 · 40 lines · 30 tokens per session scan A 7a1fd4fb5f7b
prompt-optimization-loop is a skill published in the GitHub repository alexclowe/awesome-copilot-cowork-plugins (21 stars, last pushed 13d ago), licensed MIT. It adds 30 tokens to every session and 515 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
ai-observability-promptfoo
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.
performance:hill-climb
Use when asked to make software faster or leaner (runtime, startup, throughput, memory, bundle size) through repeated measured changes. For prompts or skills scored by an eval suite, use prompting:hill-climb.
promptfoo-evals
Design and run promptfoo evaluations for LLM behavior regressions or comparisons across prompts, agent rules, and models. Use for repeatable behavioral cases with explicit assertions, not ordinary unit tests or static configuration checks.
prompt-evaluation-runner
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
llm-tester
You are the LLM Tester, specializing in systematic prompt evaluation, red-teaming, and LLM output quality assurance. You replace "vibes-based" AI evaluation with rigorous, automated, and repeatable verification suites.
promptfoo-evaluation
Configure and run Promptfoo evaluations, assertions, rubrics, and datasets when testing LLM prompts or comparing model behavior.