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 MrBinnacle/azimuth --skill research-scoutgit clone --depth 1 https://github.com/MrBinnacle/azimuthWrote 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/mrbinnacle/azimuth/research-scout)<a href="https://agentmods.dev/skills/mrbinnacle/azimuth/research-scout"><img src="https://agentmods.dev/badge/skills/mrbinnacle/azimuth/research-scout/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/mrbinnacle/azimuth/research-scout"><img src="https://agentmods.dev/badge/skills/mrbinnacle/azimuth/research-scout.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 | $0.00060 | $0.01165 |
| Opus 5 | $0.00030 | $0.00583 |
| Sonnet 5 | $0.00012 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
research-scout 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 8d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Scout
Maintain AZIMUTH's empirical integrity by tracking source publications and staging updates to references/base-rates.md.
This skill has two modes. Trigger is determined from the user's request.
SCOUT — Search for new publications. Stage validated findings.
PROMOTE — Review research/staged-findings.md. Promote, hold, or discard each staged entry.
Trigger PROMOTE when user says "promote," "review staged findings," or "what's in the queue."
Source Map
references/base-rates.md draws from 8 source families. Each has a day-of-week assignment. Do not search all groups every run.
| Day | Source Family | What constitutes a finding |
|---|---|---|
| Mon | Standish CHAOS + PMI Pulse of the Profession | New annual edition; changed on-time/overrun rates |
| Tue | CB Insights startup failure reports | New edition (last known: 2021); updated failure-cause percentages |
| Wed | BLS Business Employment Dynamics | New annual entrepreneurship/survival cohort tables |
| Thu | McKinsey large IT projects + transformation research | New survey citing overrun or value-delivery figures |
| Fri | Nielsen Breakthrough Innovation + consumer launch research | New consumer product failure rate data |
| Sat | Pendo Feature Adoption + B2B SaaS adoption research | New feature utilization dataset |
| Sun | Schmidt & Hunter follow-on meta-analyses + KPMG/Bain M&A + Flexera State of the Cloud | New predictive validity meta-analysis; M&A value-destruction update; cloud migration overrun data |
SCOUT Mode
Step 1 — Search
For today's source family, run:
WebSearch:"[source name]" [current year] reportWebSearch:site:[publisher domain] [topic] [current year]
Maximum 3 searches per source family. Do not search topics outside the assigned family.
Step 2 — Filter
Keep only:
- New edition or meaningful update to a previously cited source
- Data that materially changes a figure in
references/base-rates.md(direction reversal, or >15% change in a cited rate) - A new rigorous source that improves on a currently hedged or weakly attributed claim
- Retraction or significant methodological critique of a currently cited source
What ships with it
1 file 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.
- 8d ago First seen · 124 lines · 60 tokens per session scan A db59c53ad30e
research-scout is a skill published in the GitHub repository MrBinnacle/azimuth (8 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,165 once invoked, about $0.0003 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
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
ai-shaped-readiness-advisor
Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.
company-intel
Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.
lean-ux-canvas
Guide teams through Lean UX Canvas v2. Use when framing a business problem, surfacing assumptions, and defining what to learn next.
prd-development
Build a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative.