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 anotb/management-consulting-plugin --skill client-deliverablesgit clone --depth 1 https://github.com/anotb/management-consulting-pluginWrote 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/anotb/management-consulting-plugin/client-deliverables)<a href="https://agentmods.dev/skills/anotb/management-consulting-plugin/client-deliverables"><img src="https://agentmods.dev/badge/skills/anotb/management-consulting-plugin/client-deliverables.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00890 |
| Opus 5 | $0.00032 | $0.00445 |
| Sonnet 5 | $0.00013 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
client-deliverables 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Deliverables
Turn the analysis into an artifact that enables the intended decision and survives scrutiny. Establish the audience, decision, evidence base, requested format, and reading or presentation conditions from the user's context. Preserve supplied templates, branding, section order, accessibility needs, and length constraints.
Use available evidence and complete the portions it supports. Mark missing proof points or pending decisions where they matter; ask only when a missing answer blocks a useful result. Do not invent a number, source, owner, date, testimonial, or case result to fill a design. Distinguish proposed actions from agreed commitments.
Build the argument
Lead with the answer, decision request, or the uncertainty that prevents a decision. Organize supporting arguments by what the audience needs to assess the recommendation. Situation-complication-question-answer can help develop the story; it does not require delaying the answer or showing those labels.
Use takeaway titles for analytical sections and slides when they aid comprehension. Keep navigational labels or prescribed headings where the template requires them. The headline must be supported by the exhibit and its qualifications. Do not turn an association into a causal claim or a forecast into an achieved result.
Connect each consequential claim to its source or calculation. Keep units, periods, definitions, and scenario names consistent throughout. Show contradictions and decision-changing limitations near the claim they qualify. Separate observed results, forecasts, judgment, and illustrative examples. A conditional sentence still needs a basis if it asserts an empirical pattern.
Concentrate detail on the trade-offs, financial and operational implications, and actions that determine this decision. Use compact tables for comparisons and prose for reasoning. There is no required sentence count, supporting-argument count, or deck length.
Choose the artifact
Follow an explicit format request. If the format is open, a memo or report suits asynchronous scrutiny; a presentation suits a discussion with visual evidence. A read-ahead deck needs more self-contained explanation than a projected presentation. Produce multiple formats only when requested or needed for the stated use.
What ships with it
5 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.
- yesterday Changed · -170 lines · -39 tokens per session 7101c5413759
- 8d ago First seen · 215 lines · 102 tokens per session scan A c1c02fca8b31
client-deliverables is a skill published in the GitHub repository anotb/management-consulting-plugin (49 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 890 once invoked, about $0.0003 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
wowerpoint
Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.
save-as-pdf
Reformat the current HTML design into a paginated, paper-ready PDF. The "Instant" export already gives the user a PDF at the design's native pixel size — this path is for when they want real pages.
box
Box manages cloud files, sharing, search, and metadata.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…