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 skills add beingmartinbmc/jambavan --skill using-jambavangit clone --depth 1 https://github.com/beingmartinbmc/jambavanWrote 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/skills/beingmartinbmc/jambavan/using-jambavan)<a href="https://agentmods.dev/skills/beingmartinbmc/jambavan/using-jambavan"><img src="https://agentmods.dev/badge/skills/beingmartinbmc/jambavan/using-jambavan.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 | $0.00047 | $0.02344 |
| Opus 5 | $0.00023 | $0.01172 |
| Sonnet 5 | $0.00009 | $0.00469 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
using-jambavan 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Jambavan
Overview
Jambavan is an MCP server that provides AST-aware code indexing, token-budgeted context, durable memory, an inferred code graph, and guarded file/shell tools. It does not call an LLM — it gives you the ground to reason from.
Core principle: Index first, context before reading, memory before repeating, failures before retrying.
Session Protocol
Use this sequence for a new project session:
jambavan_doctor {}— readProject rootand itssourcebefore anything else, along with gates, storage, and index/watcher status. Every repository-bound tool fails closed while the root is an unresolvedcwd-fallback.jambavan_awaken {}— loads the protocol and recent project memories. Pass{ "root": "/absolute/repo/path" }when the root is unresolved or belongs to another repo. A root a model set earlier (source: tool-input) is re-pointed cleanly — the server stops the old watcher and closes the old index first — which is what lets one shared server process serve several workspaces. A root fromJAMBAVAN_ROOT, the host'sroots/list, or the server's own working directory is immutable and fails withroot is already fixed by ...; do not retry it.jambavan_index {}— builds or refreshes the AST-aware code index; it accepts the same optionalroot.jambavan_watch { "action": "start" }— keeps the index live while you edit (skip for one-shot tasks).jambavan_context { "query": "<task-specific query>" }— pulls ranked, token-budgeted context before reading unfamiliar code.
Quick Reference
| Need | Tool | Key options |
|---|---|---|
| Understand unfamiliar code | jambavan_context |
query, compress_prose, include_diff, include_tests |
| Trace callers/callees | jambavan_graph |
action: query, query, direction |
| Find path between symbols | jambavan_graph |
action: path, from, to |
| Graph overview / hotspots | jambavan_graph |
action: report |
| Persist a decision | jambavan_memory_store |
title, body, optional scope |
| Search past decisions | jambavan_memory_read |
query, optional scope |
| Fetch one memory by ID | jambavan_memory_read |
id |
| Wake up with active memories | jambavan_memory_read |
optional scope, limit (default 20) |
| Distill session into memories | jambavan_memory_mine_session |
text, optional scope |
| Retire a memory | jambavan_memory_forget |
id; mode defaults to the reversible invalidate, pass delete to destroy |
| Record a dead end | jambavan_failure_store |
command, symptom, optional root_cause |
| Check before retrying | jambavan_failure_search |
query, optional scope |
| Hand off to next session | jambavan_session_handoff |
optional scope, share_safe |
| Resume from handoff | jambavan_session_handoff |
text, optional scope |
| Prepare review context | jambavan_review_pack |
base, max_files |
| Compress verbose prose (write-enabled sessions) | jambavan_compress_prompt |
path, optional in_place, backup |
| Audit shortcut debt | jambavan_debt_ledger |
— |
| Investigate bug/failure root cause | root_cause prompt |
symptom, context, attempts_so_far |
| Verification gate before completion | verify_gate prompt |
claim, type |
| Sequence multi-step task strategy | strategy_plan prompt |
task, constraints, scale |
| Decompose task to parallel units | decompose_task prompt |
task, units, constraints |
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.
- 6d ago First seen · 142 lines · 47 tokens per session scan A a09066058133
using-jambavan is a skill published in the GitHub repository beingmartinbmc/jambavan (2 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 2,344 once invoked, about $0.0002 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
tdd-with-memory
A test-first implementation workflow that recalls past decisions, conventions, and lessons before coding. TDD, or test-driven development, means writing a failing test first, then implementing the code and finally cleaning it up.
diagnose-with-memory
A bug-diagnosis workflow that uses records of earlier failures, decisions, and lessons. It checks whether past findings still apply to the current version and environment before investigating the code.
Context Doctor
Identify and repair degradation in system prompt, external memory, and skills preventing you from following instructions or remembering information as well as you should.
memanto-companion
Inspect and manage the cross-session engineering memory that Memanto maintains for your Claude Code skills. Use when the user asks what Memanto remembers, wants to see their engineering profile, manually recall context for a skill, or store a decision. The automatic lifecycle hooks handle capture/injection on their…
system-monitor
Monitor system health: CPU, memory, disk, processes, and network. Alert on thresholds via any channel.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.