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 manishiitg/coding-agent-loop --skill discovery-to-reviewed-proposalgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/discovery-to-reviewed-proposal)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/discovery-to-reviewed-proposal"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/discovery-to-reviewed-proposal/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/manishiitg/coding-agent-loop/discovery-to-reviewed-proposal"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/discovery-to-reviewed-proposal.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 | $0.00029 | $0.00718 |
| Opus 5.5 | $0.00012 | $0.00287 |
| Sonnet 5.5 | $0.00006 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
discovery-to-reviewed-proposal 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 20d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery to Reviewed Proposal
Outcome
Prepare one exact-meeting brief and one unsent proposal for the same account and opportunity. The proposal uses reviewed post-call discovery notes and current approved pricing. A prepared brief, meeting held, proposal approved and proposal sent are distinct states.
When to use
Use when a SaaS seller connects discovery and proposal work across owners or access boundaries. Call Briefing and Proposal Drafter are required; Account Researcher is optional. One Crew can handle a compatible manual case.
Discovery and user direction
Inspect existing Crews, meeting and opportunity IDs, CRM and calendar source, approved product claims, discovery-note process, price list, discount authority and proposal owner. Ask for missing scope. Show the concrete Crew and step plan before Builder applies it. No selected template sends a proposal.
Required inputs
Bind tenant, account, opportunity, meeting, seller, time zone, offer, approved source scope, post-call notes version, pricing version, currency, commercial owner, format and review policy. If the call has not occurred or notes are not approved, stop at the meeting brief and leave the proposal step pending.
Plan and AgentWorks tools
Create steps for Call Brief, blocking validation, seller-confirmed discovery note, Proposal Draft and blocking validation. The brief emits sales-call-brief/v1; the proposal cites that exact brief and a separate approved note revision, approved offer and price IDs. Pass bounded references through a Crew attachment. Re-read opportunity and pricing before drafting. If a separately approved route later sends the proposal, require exact recipient, version, owner approval, current-state check, idempotency key and provider receipt.
Knowledge and persistence
Keep account, opportunity and meeting IDs; invite and CRM revisions; approved discovery note ID; source and pricing versions; proposal version; owner corrections; validation results; approval state; and any delivery receipt. On repeat, compare these exact versions and preserve an approved or sent version.
What ships with it
8 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.
- 20d ago First seen · 48 lines · 29 tokens per session scan A bd2c2aa3fd08
discovery-to-reviewed-proposal is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 718 once invoked, about $0.0001 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 2026-09-27.
Other skills, from other repositories
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.
craft-studio
Router for the ArtCraft craft apps (PhotoCraft, VectorCraft, FilmCraft, LightCraft, PdfCraft, EffectCraft, DesignCraft, FigCraft, WordCraft, SoundCraft, DeckCraft, CADCraft, GridCraft) driven headless via pi-craft. Use to choose which app fits a job and run the discover-execute-save-verify loop - "which craft app…