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.
git clone --depth 1 https://github.com/widnyana/eyay-toolkitsWrote 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/commands/widnyana/eyay-toolkits/cg)<a href="https://agentmods.dev/commands/widnyana/eyay-toolkits/cg"><img src="https://agentmods.dev/badge/commands/widnyana/eyay-toolkits/cg.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00553 |
| Opus 5 | $0.00006 | $0.00277 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
cg 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 7d 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.
What it actually says
Extract (if target is existing code) or sketch (if target is a task) the call graph for: $ARGUMENTS
Apply the Design Graph method — nodes are functions, edges are data flow.
Graph Protocol — quick reference
Emit ALL sections below, in this order, with these markers:
PROBLEM: <one line>
X → DesignGraph<A, E, R>
│ │ │ │ │
│ │ │ │ └─ R: what each node needs (§5)
│ │ │ └──── E: where the graph breaks (§4)
│ │ └─────── A: what flows through nodes (§2)
│ │
│ └─ nodes = functions, edges = data flow
│
└─ the problem
SHAPES: records · IDs · state variants · named errors
GRAPH: ascii call graph, annotated inline:
R: deps · E: err ⟳retry[×n] → ↯escape(alt) | ☠die · 🔒 unknown→trusted
CARDINALITY: node (1) one-shot · (N) many over time · (T) time-bounded
BOUNDARIES: every untrusted→trusted crossing (parse, don't validate)
BEHAVIOR: orthogonal layers (retry, cache, logging) that wrap without changing the graph
SCOPE: resources: acquire@x → release@x (structural, not convention)
TEST LAYERS: the R tests provide — same GRAPH, zero code change
VERDICT: code matches graph? happy path free of error handling? E fully enumerated?
Rules
- The graph is the ground truth. For existing code, reconstruct the graph the code ACTUALLY implements — not what the author intended.
- Every node gets cardinality +
R:. Every failure gets⟳,↯, or☠. Every trust crossing gets🔒. - Adapt vocabulary to the target language/stack (exceptions vs Result types, RAII vs context managers, etc.) — never the discipline.
- If you find nodes that violate the method (tangled happy path, unscoped resources, hidden dependencies), list them under VERDICT, grouped by § number.
If the full spec is needed, use the graph-protocol skill (notation) and the
design-method skill (the method) shipped in this plugin.
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.
- 7d ago First seen · 50 lines · 13 tokens per session scan A a2481df54293
cg is a command published in the GitHub repository widnyana/eyay-toolkits (7 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 553 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
techdebt
Find and report technical debt in the codebase.
debug
Structured platform troubleshooting — classifies the problem layer, collects evidence, forms a root-cause hypothesis, and proposes a fix with validation and rollback steps.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.
deep-code-analysis
Comprehensive codebase investigation using research-expert for documentation, explore-codebase for structure, and deep analysis. Perfect for understanding complex systems.
watch
Check for Claude Code updates, detect breaking changes, analyze plugin compatibility, and optionally gather community pulse via Exa.
fix
Quick bugfix commit. Use for fix bug, bugfix, patch, hotfix, correct error.