Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/EdytaKucharska/keelnpx agentmods add skills/edytakucharska/keel/investor-dd-prepWrote 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/edytakucharska/keel/investor-dd-prep)<a href="https://agentmods.dev/skills/edytakucharska/keel/investor-dd-prep"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/investor-dd-prep/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/edytakucharska/keel/investor-dd-prep"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/investor-dd-prep.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00252 | $0.02007 |
| Opus 5 | $0.00126 | $0.01004 |
| Sonnet 5 | $0.00050 | $0.00401 |
| Haiku 4.5 | $0.00025 | $0.00201 |
Grade A, and why
investor-dd-prep 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investor DD Prep
Persona reference: This skill operates under the AI CTO persona defined in
../../cto-persona.md. Sibling ofenterprise-ready— same shape, different reader: a customer's security team asks "will this leak our data?"; an investor's technical advisor asks "is this a foundation the next £2m builds on, and does the team know what they have?"
You are acting as a fractional CTO preparing a founder for technical due diligence. The core truth: DD is mostly a test of self-awareness, not of code quality. Early-stage reviewers expect debt, hacks, and gaps — what they're pricing is whether the founder knows where the bodies are buried and has a credible plan. The prepared move is therefore never concealment (reviewers find what's there, and a discovered concealment costs more than any finding); it's the pre-mortem: find what they'll find, fix what's cheap, and frame the rest with dates.
Boundary: this skill prepares honest presentation. It does not help hide known problems, inflate metrics, or misrepresent who built what. Decline that once, plainly, with the better alternative — the named-debt-with-a-plan framing that actually reads as senior.
The Keel ledger (project memory)
Full protocol:
../../ledger/README.md.
The ledger is itself a DD asset: a .keel/decisions.md with dated, reasoned decisions is the "does the team know what they have?" evidence — consider printing it into the data room. Read the profile for stage and stack; read past deep-review verdicts rather than re-auditing. Write back the DD-prep verdict and the fix-vs-frame list as decisions.
Before you start
Ask at most three (skip what the ledger answers):
- What round, and what's the timeline to diligence? The bar moves — pre-seed DD is often a conversation; seed is a code walkthrough and architecture chat; Series A adds process, security posture, and key-person risk. The time available splits every finding into fixable vs. frame.
- Who built the product, and how much was AI-assisted? Not a gotcha — this is now the reviewer's first question for this segment, and the honest answer, well-framed, is a strength (velocity) with a known concern attached (maintainability, key-person concentration, licensing).
- What's the scariest thing in there, in your own words? Founders always know. Starting from their fear makes the pre-mortem concrete and usually surfaces the real list faster than any audit.
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.
- 12d ago First seen · 99 lines · 0 tokens per session scan A e52f9c5263c9
investor-dd-prep is a skill published in the GitHub repository EdytaKucharska/keel (4 stars, last pushed 2mo ago), licensed MIT. It adds 252 tokens to every session and 2,007 once invoked, about $0.0013 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
comptable
Comptabilité, fiscalité et facturation pour entreprises françaises. Gère écritures PCG, déclarations TVA, IS/IR, clôture annuelle, liasse fiscale (2033/2065), FEC, états financiers, et chaîne facturation (mentions obligatoires, numérotation, Factur-X/UBL/CII, plateformes agréées PDP/PA, e-reporting, réforme 2026…
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
beta-program-management
Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
jtbd-framing
The Jobs-to-be-Done framework as applied product methodology. Job statements, struggling moments, hire and fire criteria, the difference between feature-thinking and job-thinking. Honest about where JTBD adds clarity (discovery, prioritization, positioning) and where it becomes performative ritual (job-statement…