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 vendor-evaluation-to-purchase-decisiongit 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/vendor-evaluation-to-purchase-decision)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/vendor-evaluation-to-purchase-decision"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/vendor-evaluation-to-purchase-decision/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/vendor-evaluation-to-purchase-decision"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/vendor-evaluation-to-purchase-decision.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 | $0.00024 | $0.00732 |
| Opus 5.5 | $0.00010 | $0.00293 |
| Sonnet 5.5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
vendor-evaluation-to-purchase-decision 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendor Evaluation to Purchase Decision
Outcome
Compare exact vendor plans against one approved requirement revision and total-cost basis, then prepare a current purchase decision. A shortlist is not procurement approval or a purchased service.
When to use
Use when a business is choosing among vendors and needs a separate budget or procurement owner to review the choice. A standalone Vendor Researcher suffices for early exploration. A single bill already received belongs in Invoice Intake to Reviewed Payable.
Discovery and user direction
Builder inspects existing Vendor Researcher and Spend & Payables Coordinator Crews, their owners and access. Agree on the buyer need, candidate set, legal entity, decision owner, source freshness and action boundary. Propose reuse, exact handoff and a manual case before configuration. Selection starts no vendor contact or purchase.
Required inputs
Bind one request ID, requirement revision, must-haves, weights, region, exact plan and quote revisions, seat count, term, common currency, all known fees, budget, current vendor/subscription/PO source, security/privacy policy and approver. Unknown quote or gate evidence stays unknown.
Plan and AgentWorks tools
Workflow steps: Vendor Researcher cites dated plan, quote and criterion sources and emits vendor-comparison/v1. Its cost arithmetic and must-have states must pass the validator before Payables reads it. Spend & Payables Coordinator re-reads current vendor, overlapping commitments, budget and policy records; emits vendor-purchase-review/v1 bound to the selected exact quote. Validate the pair. Ask the named owner to review or return blockers. Any vendor creation, PO, signature, payment or external message needs a separate approved action and provider receipt.
Knowledge and persistence
Keep request and entity IDs, requirement revision, source and quote revisions, cost assumptions, gate decisions, case key, owner receipt and provider IDs. Repeat reads current offers, budget and vendor state; an expired quote or changed plan requires a new comparison.
What ships with it
10 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.
- examples/invalid-vendor-purchase-review.json 1.7 KB
- examples/vendor-comparison.json 3.3 KB
- examples/vendor-purchase-approved.json 1.9 KB
- examples/vendor-purchase-blocked.json 1.8 KB
- examples/vendor-purchase-pending.json 1.7 KB
- playbook.json 4.2 KB
- references/team-and-handoffs.md 2.4 KB
- scripts/test_validate_handoff.py 4.2 KB runs code
- scripts/validate_handoff.py 14 KB runs code
- SETUP.json 2.7 KB
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 · 49 lines · 24 tokens per session scan A a10202e722e4
vendor-evaluation-to-purchase-decision is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 24 tokens to every session and 732 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
agency-french-consulting-market-navigator
Navigate the French ESN/SI freelance ecosystem — margin models, platform mechanics (Malt, collective.work), portage salarial, rate positioning, and payment cycle realities.
weekly-update
OpenDesign's weekly metrics standup: this week's numbers, the one anomaly, and the single decision it forces. Built as a decision-grade data & finance deck for ops & growth team.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
machinist
Use Machinist to create, assign, and monitor software tasks. Use when a coding agent needs to work with Machinist, its GitHub issue workflow, intake labels, direct runs, or managed queue.
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…
gridcraft
Headless spreadsheets with GridCraft (XLSX/CSV/TSV workbooks, formula evaluation, recalculation, PDF export), provisioned on demand by pi-craft. Use for "build a budget spreadsheet with formulas", "convert this xlsx to csv", "what does this formula evaluate to", "change a cell and recalculate the totals", "export the…