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 skills/bostonaholic/team/hownpx skills add bostonaholic/team --skill howgit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/how)<a href="https://agentmods.dev/skills/bostonaholic/team/how"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/how.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 | $0.00128 | $0.02237 |
| Opus 5 | $0.00064 | $0.01118 |
| Sonnet 5 | $0.00026 | $0.00447 |
| Haiku 4.5 | $0.00013 | $0.00224 |
Grade A, and why
how 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 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.
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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How — Architectural Explanation
Explore the codebase to answer "how does X work?" Produce the mental model a senior engineer needs to start working in an unfamiliar subsystem — the architecture, the flow, and the sharp edges. Not annotated source code.
Companion to skills/why/SKILL.md: how answers what the code does and
how it works; why answers what forces led to its shape. When the user
asks about motivation, rejected alternatives, or history, that is why's
job.
This skill is read-only. It writes no files, records no artifacts, and changes no state — in this session and in every subagent it dispatches.
Two modes:
- Explain (default) — explore and produce a clear explanation.
- Critique — explain first, then dispatch fresh-context critics to judge the architecture.
Input
$ARGUMENTS is the question — a subsystem ("the rate limiter"), a
feature flow ("what happens when a user submits the form"), or a
placement question ("where should this validation live"). Two resolution
paths:
- Given — parse the target and scope directly from the argument.
- Empty or vague — infer the target from conversation context: open files, recent edits, what was just discussed. State your interpretation in one line before exploring so the user can redirect if you are off. Do not ask first; a stated best guess beats a questionnaire.
Choose the mode from the ask: a request for problems, issues, or improvements ("critique the architecture", "what's wrong with this design") selects Critique; everything else is Explain.
Explain mode
Follow
skills/principle-progress-tracking/SKILL.md: when this procedure has two or more steps, seed one todo item per step before starting and mark each complete as you go.
- Assess complexity. A single module, one utility, or a narrow "how does function X work" is simple. A subsystem spanning many files or services, a cross-cutting feature flow, or a full architectural overview is complex. When in doubt, lean simple — you can still fan out later if you hit a wall.
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.
- yesterday First seen · 203 lines · 128 tokens per session scan A 5c5045b97116
how is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 2,237 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.
java-optionals-eval-capture
Use in Symphony for Trello when a Java change or review presents a reusable Optional or absence/fallback strategy-selection lesson, including on an adjacent owning API such as ScopedValue even when no java.util.Optional appears. Capture the before/prompt/after code and create or update a self-contained eval issue in…
java-streams-eval-capture
Use in Symphony for Trello when a Java change or review presents a reusable lesson about choosing or preserving a stream, collector, direct result-producing collection transformation, or character-predicate traversal, including identity or delimited string reductions, even when the preferred final code contains no…
continuous-learning
Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.
agent-challenges
Agent skill for challenges - invoke with $agent-challenges.
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…