Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jakeintech/waybill/plugin install waybillWrote 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/jakeintech/waybill/disclose)<a href="https://agentmods.dev/skills/jakeintech/waybill/disclose"><img src="https://agentmods.dev/badge/skills/jakeintech/waybill/disclose.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 | $0.00135 | $0.01082 |
| Opus 5 | $0.00068 | $0.00541 |
| Sonnet 5 | $0.00027 | $0.00216 |
| Haiku 4.5 | $0.00014 | $0.00108 |
Grade A, and why
disclose scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disclose
"Was AI used here?" is being asked by more policies every quarter — journal submissions, open-source projects, client contracts, internal AI-use registers. Most people can only answer from memory. A waybill user answers from the meter: per shipped item, what Claude's role was and what it metered, conservation-checked. The register is the individual's to produce and hand over per item, on their initiative — disclosure is something the user does, never something done to them.
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" mine --all # catch-up metering first, always
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" query report --from <iso> --to <iso> --audience internal
"${CLAUDE_PLUGIN_ROOT}/bin/waybill" query story <KEY> # single-item disclosure
Single item — "was AI used on KEY?"
One paragraph, from the item's shipped row (query report, or
query story <KEY> for the spend detail):
PLAT-482 — Retry logic for checkout webhook. Claude role: co-wrote. 2 metered sessions, 1.5M tokens attributed ($4.20 list-price equivalent, rates 2026-08-01). Shipped 2026-08-12 (PR #1932). Metering is deterministic and conservation-checked (
waybill verify); attribution confidence and the event ids behind this statement are available on request.
claude_role is the user's own declaration, recorded at logging time —
say "recorded role", not a measured fraction of authorship. The measured
part is sessions/tokens; keep the two clearly labeled. A role of none
with metered tokens deserves one honest line ("tokens metered on this
story, role recorded as none — likely research/review context") rather
than silent omission.
The register — a window's disclosure table
From .data.shipped, one row per item:
| Item | Role (recorded) | Sessions | Tokens | Token share | Shipped |
|---|---|---|---|---|---|
| KEY — title | co_wrote | 2 | 1.5M | 34% of window | date + PR |
- Token share = row
metered_tokens/costs.window_tokens— label the denominator ("of this window's metered spend"). Never present it as "% of the code Claude wrote"; tokens measure assistance volume, not authorship. - Include items with role
none— a register that lists only AI-touched items can't prove a negative. "No AI assistance recorded" is the valuable answer for those rows. - Footer, always: metering basis (deterministic, from local transcripts,
conservation-checked), the window,
pricing_versionif dollars appear, and unattributed % — a register hiding unattributed spend isn't a register.
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.
- 5d ago First seen · 95 lines · 135 tokens per session scan A 7ce436cf1c8c
disclose is a skill published in the GitHub repository Jakeintech/waybill (1 stars, last pushed 13d ago), licensed MIT. It adds 135 tokens to every session and 1,082 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
internal-controls-and-audit
Designs and tests controls over financial reporting — segregation of duties, approval limits, evidence, and preparing for audit. Use this to design controls for a process, prepare for an external audit, respond to an audit finding, set approval thresholds, or assess where a small team's segregation of duties is…
chief-legal-and-risk-officer
Owns legal, contracts, intellectual property, regulatory compliance, privacy, security governance, enterprise risk, and audit readiness. Use this to review a contract or commitment, assess regulatory or privacy exposure, evaluate an IP or licensing question, judge the risk in a business decision, prepare for an audit…
intellectual-property
Covers what the organization owns and what it is only borrowing — trademarks and clearance, copyright and work-for-hire, patents and trade secrets, open-source license obligations and copyleft reach, and IP terms in customer, contractor and AI-tool agreements. Use this to check whether a name is usable, establish that…
chief-human-resources-officer
Owns the organization itself: org design, hiring, performance, compensation, development, culture, and employee relations. Use this to design or restructure a team, plan hiring, write a role or leveling definition, handle a performance or compensation question, diagnose why a team is underperforming for non-technical…
deal-negotiation
Negotiates a commercial deal without giving away the terms that matter — preparing your walk-away and theirs, trading concessions rather than conceding them, recognizing the tactics that create false urgency, protecting price by moving other variables, and closing on terms someone can actually deliver. Use this to…
capital-structure-and-covenants
Decides how the business is financed and what that financing then requires of it — debt versus equity, weighted average cost of capital as a hurdle rate, how much leverage cash flow can carry, and the financial, affirmative and negative covenants, definitions, test dates and cure rights that come attached. Use this to…