Kungfu is a work-continuity system that lets the same task move between coding agents such as Codex, Claude, and OpenCode without losing its context or progress. It is for people coordinating different agents across attempts, reviews, failures, and recoveries, while the catalogue skills and instructions define agent workflows around that shared work.
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 kungfu-systems/kungfu --skill ampgit clone --depth 1 https://github.com/kungfu-systems/kungfuWrote 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/kungfu-systems/kungfu/amp)<a href="https://agentmods.dev/skills/kungfu-systems/kungfu/amp"><img src="https://agentmods.dev/badge/skills/kungfu-systems/kungfu/amp/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/kungfu-systems/kungfu/amp"><img src="https://agentmods.dev/badge/skills/kungfu-systems/kungfu/amp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00843 |
| Opus 5 | $0.00016 | $0.00421 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
kungfu-agent-onboarding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- kungfu-agent-onboarding — 97% identical, 11 lines differ
What it actually says
Kungfu Agent Onboarding
When KUNGFU_AGENT_ENVIRONMENT=native-interactive, use the in-process
environment envelopes before acting:
KUNGFU_AGENT_CONSOLE_ENVELOPEidentifies the exact Project, WorkConsole, SessionAttempt, runtime Profile, and optional WorkRef.KUNGFU_SKILL_CONTEXTadvertises the compact Skill catalog. Load full Skill instructions only through the declared Kungfu entrypoint.KUNGFU_AGENT_CONTEXTand its entrypoints are discovery pointers, not a prior chat transcript.KUNGFU_PRIOR_TRANSCRIPT_BYTES=0means continuity comes from Core evidence, never hidden provider conversation state.
Confirm current facts with read-only commands when needed:
"$KUNGFU_CLI_BIN" agent console current --json
"$KUNGFU_CLI_BIN" agent bootstrap-status --json
"$KUNGFU_CLI_BIN" agent capabilities --json
"$KUNGFU_CLI_BIN" skill catalog --json
"$KUNGFU_CLI_BIN" work status --workspace <path> --initiative-id <id> --assignment-id <id>
"$KUNGFU_CLI_BIN" agent session list --json
A bare kungfu run amp launch is intentionally Work-unbound so many terminal
windows can start in the same Project. As soon as you choose or accept one
Assignment, and before editing files or invoking a Work mutation, run:
"$KUNGFU_CLI_BIN" agent console bind-work --initiative-id <id> --assignment-id <id> --json
Keep the provider UI available when bootstrap is pending or degraded, but do
not create, bind, or mutate Work until kungfu agent bootstrap-status --json reports
state: verified.
The plan-native-bind-work and bind-native-work capability names are
internal Session protocol operations, not public CLI entrypoints; never invoke
them through kungfu agent session.
When durable Work may reduce continuity, handoff, evidence, duplicate retry,
or external-write risk, submit only bounded structured signals to kungfu agent work-advisory --signals <signals.json> --json. Never include a transcript,
hidden reasoning, credentials, or unrelated context. For recommend, show the
returned preview and ask its single confirmation. Only after confirmation use
the returned existing kungfu.work.capture, kungfu.work.admit, and
kungfu.agent.console.bind-work path, cite its receipts, and continue the
original task. Suppress a decline for the returned evidence root until the
structured evidence changes. Advice grants no external authority.
For Skill reuse or creation, send only rooted catalog/Work/requirements evidence,
candidate roots, enums, and booleans to kungfu agent skill-advisory --signals <signals.json> --json. Consume its shared policy root
sha256:dc8ebb873760e55c40ef19b8354ba1e2b91706064a48dec00b1eb8dac0479267;
do not reproduce the decision policy in provider prose. The result is read-only.
Do not continue unless it returns status: bound. If Kungfu reports
native_work_already_active, stop this Work in the current terminal and follow
the returned guidance; never bypass the guard or become a second writer.
Do not infer Work completion from terminal output or process exit. Mutate Work only through public Profile/KFD actions and their receipts. The Kungfu TUI is an observer of this native UI and never owns Amp input or transcript bytes.
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.
- 9d ago First seen · 77 lines · 32 tokens per session scan A e45671459e67
kungfu-agent-onboarding is a skill published in the GitHub repository kungfu-systems/kungfu (4,514 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 843 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 2026-08-30.
Other skills, from other repositories
author-pragma-dsl
Create and update validated pragma/v5 Expert, ExpertTeam, Flow, Evaluation, and Automation resources. Use when a user asks Pragma to create, change, configure, test, evaluate, or repair an Expert, team, Flow, Run Dry suite, schedule, trigger, or Automation in the current Pragma project.
portable-bundle-review
A review guide for portable Pragma bundles. A portable bundle is a packaged set of resources intended to work across environments.
pragma-code-review
A code-review guide written in Chinese. It reviews code across correctness, architectural boundaries, risk, and verification.
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.