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 commands/airbone42/360-data-athlete/researchgit clone --depth 1 https://github.com/airbone42/360-data-athleteWrote 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/commands/airbone42/360-data-athlete/research)<a href="https://agentmods.dev/commands/airbone42/360-data-athlete/research"><img src="https://agentmods.dev/badge/commands/airbone42/360-data-athlete/research.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 | $0.00000 | $0.01557 |
| Opus 5 | $0.00000 | $0.00779 |
| Sonnet 5 | $0.00000 | $0.00311 |
| Haiku 4.5 | $0.00000 | $0.00156 |
Grade A, and why
research scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
note that `WebSearch` may be exhausted (the verifier works over `curl` against How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research — Evidence research for a flagged uncertainty
Resolves a concrete sport-science question with verifiable evidence and
persists the finding to framework/research/. Two entry points:
- (a) Flag-driven — a coach agent emitted a
🔬 RESEARCH-FLAG(seeframework/CLAUDE.md→ "Research-before-scaling-or-new-protocol" → agent side) and the athlete approved the research. - (b) Direct — the athlete runs
/research <question>.
Arguments
$ARGUMENTS
Optional. The research question (free text). If empty, the question is taken
from the approved RESEARCH-FLAG block currently on the table.
Workflow
Step 1: Assemble the research brief
Collect:
- question — athlete-agnostic, one concrete sport-science question (from
the flag's
questionfield or the$ARGUMENTStext). - context — what coaching decision is gated (from the flag's
decision_blocked/uncertainty, or the surrounding conversation). Background only — it must not be transcribed into the persisted document. - date —
$(date +%Y-%m-%d).
Step 2: Launch research-analyst as subagent (fresh context)
Launch the aicoach-framework:research-analyst agent as a subagent (Task
tool) — never inside the active coach pane — to guarantee fresh context.
Pass question, context, and date. The agent:
- Checks
framework/research/first; reuses an existing doc if it covers the question (no duplicate). - Otherwise researches via
WebSearch/WebFetch(primary literature first). - Persists
framework/research/<topic-slug>.mdto the schema inframework/research/README.md, athlete-agnostic (no dated incident anchors, no athlete data points). - Updates the index table in
framework/research/README.md. - Returns TL;DR + key sources + derivation + proposed downstream edits.
Step 2.5: Verify the citations (MANDATORY — before the athlete sees anything)
Launch the citation-verifier agent as a separate subagent with fresh
context. Never the agent that wrote the document, and never the head coach
pane: an author checking its own citations reproduces its own reading.
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.
- yesterday Changed · +37 lines ffc9d9b46b9b
- 5d ago First seen · 109 lines · 0 tokens per session scan A 0d3b0356188c
research is a command published in the GitHub repository airbone42/360-data-athlete (22 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,557 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
master_analysis
Run comprehensive 5-phase analysis across labs, genetics, and protocols.
replication-package
Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
arg-diagram
ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.
simulation-calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.