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 acogood/diffmode_free --skill diagnostics-intakegit clone --depth 1 https://github.com/acogood/diffmode_freeWrote 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/acogood/diffmode_free/diagnostics-intake)<a href="https://agentmods.dev/skills/acogood/diffmode_free/diagnostics-intake"><img src="https://agentmods.dev/badge/skills/acogood/diffmode_free/diagnostics-intake/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/acogood/diffmode_free/diagnostics-intake"><img src="https://agentmods.dev/badge/skills/acogood/diffmode_free/diagnostics-intake.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00125 | $0.02849 |
| Opus 5.5 | $0.00050 | $0.01140 |
| Sonnet 5.5 | $0.00025 | $0.00570 |
| Haiku 4.5 | $0.00013 | $0.00285 |
Grade A, and why
diagnostics-intake 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 1mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostics — Intake (fast founder-input)
You produce a single file: WS/01-diagnostics/founder-input.md, in the exact schema
the rest of the pipeline reads (enrichment, the constraints generator's field parser, and
synthesis all key off these sections and labels). This replaces the slow 20-minute
diagnostic interview with a ~2-minute path: research what's public, ask only what isn't.
This is capture, not analysis — no strategy, no recommendations, no channel picks. That separation is load-bearing: later stages depend on raw, un-editorialized founder context.
Inputs & Output
The invoker provides (do not hardcode absolute paths):
- MODE A —
url(a website, e.g.https://theona.ai): research the site + company. - MODE B —
answers: a block of founder answers to the minimal question set below (the orchestrator collects these in the main thread; you format them). - MODE A+B: both — research the URL AND fold in any founder answers the brief passed (answers always win over researched guesses).
- OUTPUT: write to
WS/01-diagnostics/founder-input.md(path supplied by invoker).
If neither url nor answers is present, write the schema with every must-ask field as a
[NEEDS FOUNDER INPUT: …] placeholder and report it — do not invent a business.
Field provenance (what to research vs what to ask)
| Field | Provenance |
|---|---|
| Product description, what it does, who it's for | RESEARCHABLE (homepage/about) |
| Business model + pricing (tiers, free trial) | RESEARCHABLE (pricing page) |
| Target-audience hypothesis (segments, ICP) | RESEARCHABLE (site copy) + confirm |
| Competitive alternatives (direct + indirect) | RESEARCHABLE (web research) |
| Product complexity ("explains itself" vs "needs a demo") | RESEARCHABLE + confirm |
| Stage + current metrics (visitors, signups, MRR, paying customers) | MUST ASK |
| Current acquisition sources / what's working (Q8 demand-gen signal) | MUST ASK |
| Demand-gen vs CRO split (traffic problem vs conversion problem) | MUST ASK |
| Budget (monthly marketing $, paid-ads yes/no) | MUST ASK |
| Unfair advantage / rare assets (technical skill, industry access, network, domain expertise, existing audience) | MUST ASK |
| Hours per week for growth (time they can commit) | MUST ASK |
| Goal + timeline (target metric, deadline) | MUST ASK |
| Tactics ruled out + competitor-dignity constraints | MUST ASK (optional) |
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.
- 1mo ago First seen · 224 lines · 125 tokens per session scan A 378cb13c416a
diagnostics-intake is a skill published in the GitHub repository acogood/diffmode_free (165 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 2,849 once invoked, about $0.0005 per session on Opus 5.5. 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
newsjack-detector
Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
fact-check
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
press-clip
Turn a live article URL into a press clip that looks like the real coverage — the publication's own logo, fonts, photos and layout kept intact, the ads and clutter removed, and (for a roundup) just the client's section. Renders to PDF. You inspect each site and tailor the removal; the bundled script carries no…