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 icohangar-ops/agent-conductor --skill pipeline-scoringgit clone --depth 1 https://github.com/icohangar-ops/agent-conductorWrote 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/icohangar-ops/agent-conductor/pipeline-scoring)<a href="https://agentmods.dev/skills/icohangar-ops/agent-conductor/pipeline-scoring"><img src="https://agentmods.dev/badge/skills/icohangar-ops/agent-conductor/pipeline-scoring/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/icohangar-ops/agent-conductor/pipeline-scoring"><img src="https://agentmods.dev/badge/skills/icohangar-ops/agent-conductor/pipeline-scoring.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 | $0.00040 | $0.00298 |
| Opus 5 | $0.00020 | $0.00149 |
| Sonnet 5 | $0.00008 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
pipeline-scoring 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 9d 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.
What it actually says
Pipeline Scoring
Workflow for changing the deterministic risk scoring model.
Steps
- Read
src/crm.js— locatescoreDealRisk(opportunity, account)and note the current factor weights (stale activity, missing next step, contact coverage, close-date pressure, deal size, account health). - Write or extend tests in
test/crm.test.jsfirst, with explicit assertions on scores,riskLabelboundaries, andforecastCategoryoutcomes. - Apply the weight change in
scoreDealRisk. Keep the math deterministic — no randomness, no opaque heuristics. - Run
npm testand confirm all green. - Summarize why deals now score differently — a sales manager must be able to understand every flag.
Constraints
daysUntil()uses the fixed reference date2026-05-28; never change it as a side effect of a scoring change.- Risk labels exist to surface deals needing attention, not to punish every imperfect deal — check label distribution against the fixture before and after.
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.
- 9d ago First seen · 31 lines · 40 tokens per session scan A 104ff6608418
pipeline-scoring is a skill published in the GitHub repository icohangar-ops/agent-conductor (0 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 298 once invoked, about $0.0002 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
MCP Integration Assistant
Helps design and implement Model Context Protocol (MCP) server integrations for AI agents.
MCP Server Builder
Step-by-step guidance for creating a new MCP server with FastMCP or the TypeScript SDK — tool definitions, resource handlers, error responses, and usage examples.
event-architecture-planner
Decide whether a project needs event-driven architecture, then define the smallest honest event topology and its required artifacts.
wp-cli-commands
Expert guidance for creating custom WP-CLI commands and using WP-CLI for WordPress development and administration.
acf-development
Expert guidance for creating and using ACF field groups, including repeaters, flexible content, blocks, and options pages.
rest-api-development
Expert guidance for creating custom REST API endpoints, extending existing endpoints, and working with the WordPress REST API.