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/dashaworks/report-skills/proposal-trackernpx skills add dashaworks/report-skills --skill proposal-trackergit clone --depth 1 https://github.com/dashaworks/report-skillsWrote 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/dashaworks/report-skills/proposal-tracker)<a href="https://agentmods.dev/skills/dashaworks/report-skills/proposal-tracker"><img src="https://agentmods.dev/badge/skills/dashaworks/report-skills/proposal-tracker.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 | $0.00078 | $0.00952 |
| Opus 5 | $0.00039 | $0.00476 |
| Sonnet 5 | $0.00016 | $0.00190 |
| Haiku 4.5 | $0.00008 | $0.00095 |
Grade B, and why
proposal-tracker scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- **A data room** (Business plan, see the root `SKILL.md`) gates it properly: `passcode` or per-email `allowlist` access, an NDA to accept, an expiry date, instant revocation, and per-viewer engagement. Offer this whenev How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal Tracker
The DocSend move, agent-native: publish the proposal as a live tracked page, then answer the question every sender actually has — "is it getting read?" — with view data instead of silence.
Follow the shared flow in the root SKILL.md. Proposals are maximally client-facing: approval gate always on, and double-check pricing numbers at the gate.
When to use
- The user has a proposal, quote, offer, statement of work, or pitch to send to a specific recipient
- The user asks about engagement on something already sent ("did they open it?") → go straight to
get_analytics
Steps
- Confirm the essentials before authoring. Recipient (company/person), the offer's core numbers (price, timeline, scope), and the desired next step (call booked? signature? reply?). A proposal without an explicit next step is a brochure.
- Structure for a skimming decision-maker. One-line summary of the offer up top; the "why us / why now" in one short section; scope and pricing in scannable tables; the call to action visible without scrolling far. Long context goes in an appendix.
- Author + lint + approval gate. At the gate, read back the price, timeline, and scope numbers explicitly — a typo in a published price is the worst failure mode this skill has. Note too that the page carries a small "Published with ReportRoom" footer credit the recipient will see.
- Publish with a clean slug. Return the URL and remind the user the link is tracked. When a proposal is dead or superseded, offer to
unpublishit — the link then returns 410 Gone and the plan slot frees up (republishbrings it back if the deal reopens). - The follow-up loop is the point. Offer to check views (
get_analytics) after a day or two and translate the signal into next actions: viewed-but-no-reply calls for a different follow-up than never-opened. Suggest the follow-up message to match. Be precise about what the data can say: for a published proposal it's view counts by day, not per-person opens — if one recipient got the link, views ≈ their opens; if it was shared around, it's aggregate. If the user needs to know which named person read what, that's a data room (see below), whereget_room_analyticsreports per-viewer, per-document opens and dwell.
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 · 34 lines · 78 tokens per session scan B 068f86236a5b
proposal-tracker is a skill published in the GitHub repository dashaworks/report-skills (12 stars, last pushed 29d ago), licensed MIT. It adds 78 tokens to every session and 952 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
seo-client-report
Turn a client's Search Console and analytics data into a branded monthly SEO report published as a live, tracked page via ReportRoom. Use when the user says "SEO report for my client", "monthly SEO report", "client SEO report", "SEO deliverable for". Built for consultants and agencies sending recurring monthly…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
golden-rss
Use when testing the rss golden build.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.