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 bigduu/Bamboo-agent --skill bamboo-manualgit clone --depth 1 https://github.com/bigduu/Bamboo-agentWrote 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/bigduu/bamboo-agent/bamboo-manual)<a href="https://agentmods.dev/skills/bigduu/bamboo-agent/bamboo-manual"><img src="https://agentmods.dev/badge/skills/bigduu/bamboo-agent/bamboo-manual/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/skills/bigduu/bamboo-agent/bamboo-manual"><img src="https://agentmods.dev/badge/skills/bigduu/bamboo-agent/bamboo-manual.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 | $0.00083 | $0.00594 |
| Opus 5.5 | $0.00033 | $0.00238 |
| Sonnet 5.5 | $0.00017 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
bamboo-manual 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 3d 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
Bamboo product manual
This is the offline manual embedded in this build. Read manifest.json first
and references/index.md to select a chapter. Use the package and resource
identifiers returned by skills_list / skills_read; follow next_cursor to
EOF. Preserve code blocks and whitespace. If a resource is unavailable or a
cursor expires, report that gap rather than assuming you read the whole file.
For legacy hosts that expose load_skill and read_skill_resource, load this
skill before reading resources. Request bounded line pages, follow
next_offset, and check truncated; reduce the line limit and reread that page
if it was truncated. A returned line boundary alone does not prove full bytes
were received.
- Separate product behavior from observed instance state. This bundle is product knowledge only. It cannot tell you a user's provider, paths, memory, credential values, or what a live consumer has applied.
- Locate key names in
references/config-keys.json. It is an explicitly bounded, typed-tested catalog, not a complete JSON Schema. An absent key is unverified here, not necessarily unsupported. Read the owning chapter. - Cite the manifest's package version, source revision/status, content hash,
and chapter path. Development version
0.0.0, unknown revision,checkout_unverifiedsource, dirty source archives, or missing dependency-lock identity must remain explicit. Never label this bundle the latest release or substitute online docs silently. - Give the explanation or next safe check. Only make an instance-specific
diagnosis from authorized, current evidence; state its observation time,
scope and coverage. Do not dump raw config, logs, memory, credentials or
private paths into a model request to obtain that evidence.
If available, use
bamboo_diagnosticswith no arguments for the current session's allowlisted local observations. Read troubleshooting.md for its coverage and unknown/stale-state limits. Never infer active probe success. - Reading this manual does not authorize writes, restarts, reloads, migration, repair, rebuilding memory, connecting services, model calls, enabling hooks, or hook dry-runs. Ask separately where the user's permissions require it.
The source code paths listed by each chapter are review provenance. They are not runtime dependencies and may be absent from a binary-only installation.
What ships with it
8 files 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.
- 3d ago First seen · 44 lines · 83 tokens per session scan A 2a7c9beaf92d
bamboo-manual is a skill published in the GitHub repository bigduu/Bamboo-agent (21 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 594 once invoked, about $0.0003 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 2026-10-17.
Other skills, from other repositories
ace-rsi-toolkit
Run ACE (Agentic Context Engineering, Zhang et al. 2025) on an agent the sequential offline way - a Reflector reads each training Trace, a Curator adds the lessons to a playbook of rules the agent reads before every task, and the final playbook is measured on a published Benchmark.
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …