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/patrickserrano/lacquer/handoffnpx skills add patrickserrano/lacquer --skill handoffgit clone --depth 1 https://github.com/patrickserrano/lacquerWhat 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 | $0.00088 | $0.00565 |
| Opus 5 | $0.00044 | $0.00282 |
| Sonnet 5 | $0.00018 | $0.00113 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
handoff 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 2d 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
Handoff
A handoff doc exists to save the next reader (a fresh session, a different agent, or you tomorrow) from re-deriving everything this session already figured out. Write for someone with zero memory of this conversation, not a recap for someone who was watching.
What to include
- Goal. One sentence: what this session was actually trying to accomplish.
- Done — verifiably. What's complete, stated as a fact a reader can check (a commit hash, a passing test name, a file path with the final content) — not "implemented X" without a way to confirm it.
- In-flight / blocked. What's partially done, and specifically why it stopped — a failing test with its actual output, a decision waiting on the user, an external dependency not yet available. "Ran out of time" without a concrete blocker is not useful to the next reader.
- Explicitly not done. Anything the goal implies but this session didn't touch — cheap to state, expensive for the next reader to discover by assuming it's covered.
- Next concrete step. Not "continue the work" — the literal next action: which file, which command, which decision needs making first.
- Decisions made and why. Only the ones that weren't obvious — a constraint that ruled out the default approach, a tradeoff chosen deliberately. Skip anything a reader could re-derive from the diff itself.
Where it goes
Don't silently create or overwrite a tracked file. Ask where it belongs if
unclear, or default to an untracked scratch location (e.g. a HANDOFF.md at
the repo root, gitignored, or the session's own scratchpad) — a handoff doc
is working state, not something that should land in a PR by accident.
Keep it short
If the honest answer to "what's done" is "everything, cleanly" — say that in one line and stop. A handoff doc's value is proportional to how much re-derivation it saves, not its length.
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.
- 2d ago First seen · 50 lines · 88 tokens per session scan A 16999213ce72
handoff is a skill published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 565 once invoked, about $0.0004 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
analyzing-ios-app-security-with-objection
Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
argent-react-native-optimization
Optimizes a React Native app by profiling first to find real bottlenecks, then sweeping for mechanical issues. Entry-point for all performance work. Use when the app feels slow, user asks to optimize, fix re-renders, reduce jank, or improve startup. Delegates to argent-react-native-profiler for measurement.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
argent-create-flow
Create, record, edit, replay, or repair reusable Argent flow YAML files. Use when the user asks to record or replay a repeatable device path, set up profiling or an A/B comparison, or invoke the authoring engine behind argent-qa-flows. Also use before repeating three or more interactions. For one-off UI checks…
mastg
Autonomous mobile security audit aligned with OWASP MASTG v2. Performs checklist-driven analysis across MASVS categories: storage, crypto, network, platform, code, resilience, privacy. Exports structured markdown report with MASTG test references.
spm-build-analysis
Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds. Use when a developer suspects packages, plugins, or dependency graph shape are hurting clean or incremental build performance, mentions SPM slowness, package resolution time, build…