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/linkpranay-ai/context-engineering-protocolWrote 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/linkpranay-ai/context-engineering-protocol/ult-codegraph)<a href="https://agentmods.dev/commands/linkpranay-ai/context-engineering-protocol/ult-codegraph"><img src="https://agentmods.dev/badge/commands/linkpranay-ai/context-engineering-protocol/ult-codegraph/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/linkpranay-ai/context-engineering-protocol/ult-codegraph"><img src="https://agentmods.dev/badge/commands/linkpranay-ai/context-engineering-protocol/ult-codegraph.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 | $0.00041 | $0.00392 |
| Opus 5.5 | $0.00016 | $0.00157 |
| Sonnet 5.5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
codegraph 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.
What it actually says
Read and follow the skill at .github/skills/ult-codegraph/SKILL.md.
When invoked directly by an engineer:
- Check whether
graphifyis installed (graphify --help); if not, runuv tool install graphifyy(orpipx install graphifyy). - Run
graphify update . --no-clusterto (re)generate the graph (no LLM needed — incremental on subsequent runs, only re-parsing changed files). - Optionally run
graphify cluster-only . --no-labelto also produceGRAPH_REPORT.md(community names stay generic without a configured LLM backend — that's fine, the graph data itself is unaffected and the report's God Nodes / Surprising Connections / Import Cycles sections are useful either way). - Report back: how many nodes/edges were generated, and point the user at
graphify-out/GRAPH_REPORT.mdfor the human-readable summary. Nothing to copy or normalize —graphify-out/is graphify's own fixed, predictable output location, and consuming skills query it there directly (seeCONSUMING-CODE-GRAPH.md).
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 · 33 lines · 41 tokens per session scan A 682a6225036c
codegraph is a command published in the GitHub repository linkpranay-ai/context-engineering-protocol (10 stars, last pushed 26d ago), licensed Apache-2.0. It adds 41 tokens to every session and 392 once invoked, about $0.0002 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 2026-09-08.
Other commands, from other repositories
cleanup
Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.
fix
Use for a fast bug fix with minimal ceremony (3 questions, TDD, done).
harness-audit
Use when auditing the Claude Code / AI harness setup for reliability, cost, and completeness.
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
lint-check
Runs linting and code quality checks. Catches style issues, potential bugs, and enforces project standards.
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.