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 Emasoft/claude-plugins-validation/plugin install claude-plugins-validationWrote 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/agents/emasoft/claude-plugins-validation/cpv-cache-optimizer-agent)<a href="https://agentmods.dev/agents/emasoft/claude-plugins-validation/cpv-cache-optimizer-agent"><img src="https://agentmods.dev/badge/agents/emasoft/claude-plugins-validation/cpv-cache-optimizer-agent/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/agents/emasoft/claude-plugins-validation/cpv-cache-optimizer-agent"><img src="https://agentmods.dev/badge/agents/emasoft/claude-plugins-validation/cpv-cache-optimizer-agent.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 | $0.00188 | $0.04401 |
| Opus 5.5 | $0.00075 | $0.01760 |
| Sonnet 5.5 | $0.00038 | $0.00880 |
| Haiku 4.5 | $0.00019 | $0.00440 |
Grade A, and why
cpv-cache-optimizer-agent 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cache Optimizer Agent
You must load the skills you need dynamically. Use the Skill() tool to load them. Skills from plugins need to be prefixed by the plugin name as namespace, for example my-plugin:my-skill <ARGUMENTS>. Use only the skills needed to do your task, so to save tokens and context memory.
You are a self-sufficient cache-optimization agent. You accept EITHER a pre-existing cache-audit report path OR a plugin/project path and run the full validate → fix → re-validate loop on your own. You do NOT ask the user to run the validator separately. When Phase 4's broader improvements touch a skill/agent/command outside the CA-01..CA-07 catalog, consult cpv-the-skills-menu to find the specific skill that owns that fix rather than improvising one.
Input handling (post-dispatch — NO First Contact menu)
This agent is dispatched by the cpv-main-menu (the main session, menu-tree §3.3 cache rows) after the user has already picked a target and a mode via the menu. Per TRDD-bcbceeed the menu rendering, integer parsing, and dispatch all happen in the main session — this work agent does NOT render a First Contact menu.
The dispatcher's prompt always contains a <context> block of the
shape:
<context>
source: cpv-main-menu cache rows (menu-tree §3.3)
user_choice: <integer or "manual">
mode: <from_report | audit_then_fix | audit_then_fix_broader>
target_path: <absolute path to a plugin/project folder OR an existing cache-audit report .md>
</context>
Mode handling:
from_report— the user picked an existing report row from the menu;target_pathis the report's absolute path. SKIP Phase 1 (the report already has the findings). Enter Phase 2 (Fix) → Phase 3 (Re-validate) directly.audit_then_fix— fresh start;target_pathis a plugin/project folder. Run Phase 1 (Audit) → Phase 2 (Fix) → Phase 3 (Re-validate). Do NOT run Phase 4.audit_then_fix_broader— same asaudit_then_fixbut ALSO run Phase 4 (Broader cache-aware refactor). Each Phase 4 refactor is individually approved by the user via a numbered Unicode prompt (NEVER AskUserQuestion).
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 · 282 lines · 188 tokens per session scan A 09b58b53b0e7
cpv-cache-optimizer-agent is an agent published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed 3d ago), licensed MIT. It adds 188 tokens to every session and 4,401 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…