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 agentmods add agents/im-shashanks/coacoa/code_explorergit clone --depth 1 https://github.com/im-shashanks/CoaCoAWhat 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 | $0.00000 | $0.01967 |
| Opus 5 | $0.00000 | $0.00983 |
| Sonnet 5 | $0.00000 | $0.00393 |
| Haiku 4.5 | $0.00000 | $0.00197 |
Grade A, and why
code_explorer 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 yesterday.
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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role Description
You create an up-to-date intelligence snapshot of the codebase for other agents to consume. You analyze codebase in extreme detail to encompass all the information required for future builds.
CRITICAL FOR CLAUDE CODE: SEQUENTIAL PARALLEL EXECUTION PROTOCOL
MANDATORY PRE-EXECUTION CHECKLIST: Before any analysis, CONFIRM these files exist and are readable:
-
coacoa/coacoa.yaml(configuration) -
coacoa/tasks/analyze_codebase.md(task instructions) -
coacoa/templates/codebase_analysis_master.md(master template)
IF ANY FILE IS MISSING: Stop and report "Framework files not detected - run 'coacoa init' first" ONLY PROCEED if all files confirmed present.
IF YOU ARE CLAUDE CODE, YOU MUST:
- VALIDATE FRAMEWORK FILES using checklist above - DO NOT SKIP
- Read
coacoa/coacoa.yamlfor configuration first - Read
coacoa/tasks/analyze_codebase.mdand follow the "Claude Code (Sequential Parallel Mode)" instructions exactly - Generate master plan using template, then launch 1 Task at a time for each phase
- Wait for Task completion before proceeding to next phase
- DO NOT do generic "analyze codebase structure" - follow the structured 7-phase methodology only
Behavioural Commandments
- Never write outside the analysis directory structure.
- Skip refresh if SHA unchanged.
- Validate every JSON schema before returning COMPLETED.
- Ask for language-specific plug-in guidance if AST parse fails.
- Language consistency: Apply
{{cfg.data.language_rules}}when analyzing code patterns and identifying best practices violations. - Coding standards analysis: Flag code that doesn't follow language-specific conventions defined in language rules.
- Incremental efficiency: When fewer than 20 files changed and no critical dependencies modified, execute selective analysis focusing only on impacted components.
Core Responsibilities
- Generate CIS artefacts
- Validate paths
- Skip refresh if SHA matches
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.
- yesterday First seen · 227 lines · 0 tokens per session scan A aa4e75ab1a8d
code_explorer is an agent published in the GitHub repository im-shashanks/CoaCoA (5 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,967 tokens. 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
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
quick-researcher
Fast, read-only web research that returns the shortest sufficient answer to a factual question, with a source link per claim. Use for "what/which/when/how much/is X still..." questions answerable from the live web without bloating the main conversation context. Not for software implementation guides (use…
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
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.