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 skills/sohilladhani/codesynapse/codesynapse-clinpx skills add sohilladhani/codesynapse --skill codesynapse-cligit clone --depth 1 https://github.com/sohilladhani/codesynapseWhat 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 | $0.00182 | $0.01322 |
| Opus 5 | $0.00091 | $0.00661 |
| Sonnet 5 | $0.00036 | $0.00264 |
| Haiku 4.5 | $0.00018 | $0.00132 |
Grade A, and why
codesynapse-cli 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codesynapse CLI Skill
Codesynapse has pre-indexed this codebase into a knowledge graph that knows about classes, functions, their relationships (calls, extends, implements), and source locations. The graph is more precise than grep for architecture questions.
MCP is not available in this environment. All codesynapse commands run via bash. Use the codesynapse binary — if codesynapse is not found, try /usr/local/bin/codesynapse then ~/.local/bin/codesynapse (the two standard install locations). The project graph is at ./codesynapse-out/graph.json. For global multi-module graphs, run codesynapse module list to see indexed modules.
ALWAYS use codesynapse CLI commands before grep/find for architecture questions.
Quick Reference
| Intent | Command |
|---|---|
| General codebase query | codesynapse query "<question>" --graph <path> |
| Node details + relationships | codesynapse explain <id> --path <graph-path> |
| Shortest path A → B | codesynapse path <A> <B> |
| Blast radius of X | codesynapse affected <X> --graph <path> --depth 2 |
| Graph statistics | codesynapse stats <path> |
| God/central nodes | codesynapse analyze <path> |
| Community detection | codesynapse cluster <path> |
| Module list | codesynapse module list |
| Graph diff | codesynapse diff <path> --baseline <other> |
Tool Selection Priority
STEP 1 — Architecture questions ("how does X work", "what handles Y", "where is Z defined"):
codesynapse query "<question>" --graph ./codesynapse-out/graph.json
Parse the output for class/function names, file paths, relationships. Top results are most relevant.
STEP 2 — Need details on a specific node found in Step 1:
codesynapse explain <ClassName> --path ./codesynapse-out/graph.json
Shows callers, callees, extends, implements, file path, and line number.
STEP 3 — Blast radius / change impact:
codesynapse affected <ClassName> --graph ./codesynapse-out/graph.json --depth 2
Use --depth 1 for direct dependencies, --depth 3 for wider impact. Filter by --relation calls if needed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 102 lines · 182 tokens per session scan A fcf673a76629
codesynapse-cli is a skill published in the GitHub repository sohilladhani/codesynapse (8 stars, last pushed 1mo ago), licensed MIT. It adds 182 tokens to every session and 1,322 once invoked, about $0.0009 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 skills, from other repositories
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
lean-ctx
Local context tooling for AI agents. Use it to select, shape, reuse, recover, and inspect context before inference when reading files, running shell commands, searching code, or exploring directories.
lean-ctx
Local context tooling for AI agents. Use it to select, shape, reuse, recover, and inspect context before inference when reading files, running shell commands, searching code, or exploring directories.
Sverklo Code Intelligence
Gives you deep codebase understanding — semantic search, blast-radius analysis, PR review, and health audits.
ctxo-safe-edit
Use BEFORE editing, renaming, or deleting any function, class, or method, to avoid breaking dependents.
ctxo-understand
Use at the START of any code task (fix, extend, refactor, understand) before reading source files, to orient with ctxo and avoid going in the wrong direction.