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 instructions/vohongtho/code-intel-platform/claude-mdgit clone --depth 1 https://github.com/vohongtho/code-intel-platformWhat 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 | $0.00629 | $0.00629 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
code-intel-platform CLAUDE.md 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Usage Rules (MANDATORY)
code-intel — Always Investigate First (before reading any file)
code-intel search "<concept>" # FIRST: find symbols by concept
code-intel inspect <symbol> # callers, callees, file location
code-intel impact <symbol> # blast radius BEFORE editing
- NEVER open a file cold — always
code-intel searchfirst. - NEVER grep for symbols — use
code-intel searchinstead. - NEVER edit a symbol without running
code-intel impactfirst.
rtk — Use for compact shell output
rtk read <file> # token-efficient file read
rtk grep <pattern> <file> # compact grep
rtk git log # compact git log
rtk test <cmd> # show only failures
rtk err <cmd> # show only errors/warnings
rtk diff # condensed diff
rtk smart <cmd> # 2-line heuristic summary
Code Intelligence — code-intel-platform
Auto-managed by
code-intel analyze(v1.0.5) — re-running it overwrites this block. Put durable notes below<!-- code-intel:end -->.
code-intel keeps a symbol / call-graph index of this repo. It complements reading files, it doesn't replace it — on a repo this size, read files directly for most work and reach for code-intel when you need the call graph.
Reach for it when you need
- Blast radius before changing a shared symbol —
code-intel impact <symbol>(reverse call graph). Flag ≥ 5 direct callers to the user as higher-risk. - PR review scope —
code-intel pr-impact --base master --head HEAD - Callers / callees of a symbol —
code-intel inspect <symbol> - Concept search across files —
code-intel search "<concept>" - Tracing an execution path —
code-intel query "TRAVERSE CALLS FROM '<symbol>' DEPTH 3"
CLI reference
code-intel search <query> # find symbols by concept/name
code-intel inspect <symbol> # callers, callees, imports
code-intel impact <symbol> # blast radius (who breaks if this changes)
code-intel pr-impact --base master # full PR blast radius
code-intel query "TRAVERSE CALLS FROM '<symbol>' DEPTH 3"
code-intel query "PATH FROM '<sym>' TO '<target>'"
code-intel analyze # rebuild the index (run when stale)
code-intel serve # HTTP API + web UI on :4747
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 · 53 lines · 629 tokens per session scan A 798319e26a9f
code-intel-platform CLAUDE.md is an instructions file published in the GitHub repository vohongtho/code-intel-platform (3 stars, last pushed 6d ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.