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/jakeintech/waybill/lognpx skills add Jakeintech/waybill --skill loggit clone --depth 1 https://github.com/Jakeintech/waybillWhat 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 | $0.00132 | $0.01964 |
| Opus 5 | $0.00066 | $0.00982 |
| Sonnet 5 | $0.00026 | $0.00393 |
| Haiku 4.5 | $0.00013 | $0.00196 |
Grade A, and why
log scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log Work
Record work in the ledger at the moment it happens. Follow the storage and
schema rules from the ledger skill (skills/ledger/SKILL.md in this
plugin, with references/schema.md and references/methodology.md). Read
both references before writing entries.
Use the engine for every write — invoke it as
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" <command>.
If ${WAYBILL_HOME:-$HOME/.waybill}/config.json does not exist, run ledger
initialization first (see the ledger skill).
Determine the mode
- Opening — the user is about to start a task ("I'm starting PLAT-482").
- Closing — a task just shipped ("log this, the PR merged").
- Pinning — the user asserts this session's spend belongs to a key ("pin this session to PLAT-482", "unpin").
- Mining — the user asks to process pending sessions, or unmined files
exist in
pending-sessions/when another log request comes in (mention the count, offer to mine them).
Opening a task (pre-registration — the important one)
- Ask the user for their without-Claude estimate as a range in hours,
before any work with Claude begins — once, with the one-line why (it is
what makes later time-saved claims credible). If they decline, open the
entry without an estimate (
estimate_without_claude_hours: null, nopre_registered): the item stays fully logged at facts tier, and any later time-saved claim for it will be judgment tier. Never press twice, and never backfill. - If Atlassian MCP tools are connected, fetch the issue to fill
points,epic_key,epic_name,sprint. Otherwise ask only for what's needed and leave the restnull. - Build the
openedentry body (noid) withpre_registered: true,claude_role: "none", empty artifacts, and append it:"${CLAUDE_PLUGIN_ROOT}/bin/waybill" append --stream ledger --event '<json>' --commit. The engine seals the estimate in a SHA-256 escrow automatically and refuses backdated pre-registration. - Confirm in one line, mentioning the seal the first time:
Opened PLAT-482 (5 pts) — estimate 10–16h, sealed in escrow.
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 · 159 lines · 132 tokens per session scan A bd2a0793d2c6
log is a skill published in the GitHub repository Jakeintech/waybill (1 stars, last pushed 9d ago), licensed MIT. It adds 132 tokens to every session and 1,964 once invoked, about $0.0007 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
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
performance-analysis
Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.