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/tony/skills/briefnpx skills add tony/skills --skill briefgit clone --depth 1 https://github.com/tony/skillsWrote 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/tony/skills/brief)<a href="https://agentmods.dev/skills/tony/skills/brief"><img src="https://agentmods.dev/badge/skills/tony/skills/brief.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 5.1 | $0.00035 | $0.00925 |
| Opus 5 | $0.00017 | $0.00463 |
| Sonnet 5 | $0.00007 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
brief 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 2d 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.
This is a copy
91% identical to situate-brief — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief
Someone just said "huh". Give them five lines and get out of the way.
Read ../../references/brief.md before answering — it
carries the five-line budget, the ranking that decides what earns a
line, the option-line format, and the evidence tiers. /situate:what is
the explicit entry point to this same contract.
Recognizing the trigger
The signal is a question with no subject. "What does the parser do" names what it wants and is an ordinary question. "What" on its own names nothing, because the user cannot yet articulate what they are missing — that inability is the thing to fix.
Treat these as the same ask: a bare interrogative, a request to back up, or an admission of being lost. Treat anything with a stated object as a normal question and answer it normally.
When genuinely unsure, answer briefly rather than asking which they meant. A five-line answer to the wrong reading costs less than a clarifying round-trip, and it usually reveals the right reading.
A request to be caught up is not this skill, even though it overlaps.
"Bring me up to speed on this branch", "what is this pull request
waiting on", "where did this work leave off" all name what they want and
want it in full — that is situational-awareness, and /situate is its
explicit form. This skill is for the moment before someone can phrase
that request.
The description above deliberately carries none of that vocabulary — no branch, pull request, ticket, or catching up. Routing scores terms, so naming those here to disclaim them makes this skill match the prompts it is disclaiming, and it takes them from the sweep that should own them. The boundary belongs in this body, which is read only after the skill is already chosen.
What "huh" is usually about
Rank by how recently the confusion could have started.
Most often it is the last thing that happened in the session — a command that ran, a decision taken, a direction changed without being announced. That answer is already in context and needs no tools.
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.
- 2d ago First seen · 99 lines · 35 tokens per session scan A 7aba0fbea37a
brief is a skill published in the GitHub repository tony/skills (2 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 925 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to situate-brief, differing in 19 lines, and is treated as a copy.
Other skills, from other repositories
enablement-course
Assemble an internal AI enablement course for a company's own employees, sized to where they actually are rather than where a vendor deck assumes they are. Produces the session plan, per-session content and exercises, a facilitator guide for a non-expert, and a way to tell whether it worked. Builds on the tech stack…
coaching-mode
Use when the user wants to coach someone — a report, peer, or mentee — through a problem rather than solve it for them. Trigger phrases include "coach me through how to talk to [report]", "I want to help [name] figure out X without telling them what to do", "let me practice a coaching conversation", "GROW conversation…
start
Use when the user is new to bettersense and doesn't know where to begin, or when they want a tour of what's available. Trigger phrases include "where do I start", "how do I use this", "what can you do", "what should I run first", "I just installed this", "help me get started", "what is bettersense", "how does this…
postgres-database-migration
Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases. Trigger when user asks to: Test a schema migration before applying it to production Add, remove, or rename columns safely on a live table Change a column's data…
design-postgis-tables
Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications.
setup-timescaledb-hypertables
Use this skill when creating database schemas or tables for Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. Use this to improve the performance of any insert-heavy table. Trigger when user asks to: Create or design SQL schemas/tables AND…