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/madeinoz67/madeinoz-knowledge-systemWrote 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/madeinoz67/madeinoz-knowledge-system/symbol)<a href="https://agentmods.dev/commands/madeinoz67/madeinoz-knowledge-system/symbol"><img src="https://agentmods.dev/badge/commands/madeinoz67/madeinoz-knowledge-system/symbol/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/commands/madeinoz67/madeinoz-knowledge-system/symbol"><img src="https://agentmods.dev/badge/commands/madeinoz67/madeinoz-knowledge-system/symbol.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 | $0.00027 | $0.00499 |
| Opus 5 | $0.00014 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
symbol 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 10d 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
Context
Symbol to analyze: $1
User's question: $2
Your task
Use the Bash tool to fetch symbol information, then answer the user's question.
Workflow:
- Execute:
node .claude/scripts/codanna/context-provider.js symbol $1 - Analyze the symbol details returned (includes
[symbol_id:123]for all symbols) - For deeper exploration, the script supports:
describe,callers,callssubcommands - Trust the script output. If it's not enough, ask the user.
- Answer the question: "$2"
The meta-principle is: "When given a workflow, follow it. Uncertainty is a signal to verify, not improvise."
When answering:
- Reference actual code locations (file:line_range)
- Explain relationships (calls, called_by, implements, defines)
- Use the signature and documentation from the symbol
- Be specific about how the symbol is used in the codebase
Following relationships:
- Use
<symbol_name|symbol_id:ID>for follow-up queries - Commands:
calls,callers,describeaccept either format
Focus on what the code actually shows, not general programming principles.
Graph Visualization
When the symbol has rich relationships, suggest:
"This symbol has N callers/calls. Would you like a graph visualization?"
If the user explicitly asks for a graph, or accepts the suggestion:
- Execute:
node .claude/scripts/codanna/visualize-graph.js <symbol_id:ID> [depth] - Default depth is 2 (shows immediate + one level of transitive relationships)
- The script generates an HTML file and outputs the path
- Tell the user the file location so they can open it in their browser
When to suggest graphs:
- Many relationships where text output is hard to follow
- User asks "how is this connected" or "show me the relationships"
- User wants to understand call flow or dependency topology
Do NOT suggest graphs for:
- Simple symbols with 0-2 relationships
- When user is asking about implementation details, not relationships
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.
- 10d ago First seen · 56 lines · 27 tokens per session scan A 249cc2728762
symbol is a command published in the GitHub repository madeinoz67/madeinoz-knowledge-system (3 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 499 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
maestro-odyssey
Long-running iterative cycle — one entry, seven modes (debug|improve|planex|review|security|defensive|ui). Shared archaeology/audit → fix → verify → generalize → discover → persist skeleton with mode-specific dimensions. User-invoked campaign entry; single-step fixes route via /maestro-next.
tidy-doctor
One-shot read-only doctor for skill package presence and repo hygiene.
fix
PURPOSE: Fix issues in based on feedback TASK.
diagnose
Run system health diagnostics and interpret the results.
develop-fix
Systematic bug fixing with root cause analysis and regression prevention.
gsd:debug
Systematic debugging with persistent state across context resets.