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/drubinstein/terry/brendannpx skills add drubinstein/terry --skill brendangit clone --depth 1 https://github.com/drubinstein/terryWrote 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/drubinstein/terry/brendan)<a href="https://agentmods.dev/skills/drubinstein/terry/brendan"><img src="https://agentmods.dev/badge/skills/drubinstein/terry/brendan.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 | $0.00163 | $0.03583 |
| Opus 5 | $0.00081 | $0.01792 |
| Sonnet 5 | $0.00033 | $0.00717 |
| Haiku 4.5 | $0.00016 | $0.00358 |
Grade A, and why
brendan 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 4d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brendan — systems-performance methodology (the USE method & friends)
Brendan is the measure-don't-guess discipline you run when a system is slow, saturated, or near capacity. It is Brendan Gregg's body of performance methodology — most of all the USE method — distilled into a skill: instead of reaching for whatever tool you remember (the streetlight anti-method) or blaming the component you touched last, you walk a complete list of resources and, for each, check three things — Utilization, Saturation, Errors — until the bottleneck names itself.
USE in one line: For every resource, check utilization, saturation, and errors. It finds ~80% of server issues with ~5% of the effort.
It is the generalization of three metric types applied to every resource:
- Utilization — the average time the resource was busy servicing work, as a percent over an interval. (Caveat: a 5-min average of 20% can hide 100% bursts.)
- Saturation — the degree of extra work the resource can't service, usually queued. Any non-zero saturation is a problem.
- Errors — the count of error events. Check these first: they're quick to read and easy to interpret.
…and the spine that makes it a method: a complete resource list you refuse to leave gaps in — CPUs, memory capacity, network interfaces, storage device I/O, storage capacity, storage/network controllers, and the CPU/memory/I/O interconnects — each crossed off only when U, S, and E are all accounted for.
When to use
Use Brendan whenever you face a resource-bottleneck or capacity question and want a systematic sweep instead of a hunch. Typical shapes:
- "the box/app/cluster is slow" with no obvious cause — run the sweep
- a latency or throughput regression you need to localize to a resource
- capacity planning / "are we near a limit?" / headroom questions
- a saturation symptom (rising queues, tail latency, page-ins, packet drops)
- GPU under-utilization or stalls in an ML/HPC job — note
nvidia-smi"GPU-Util" = any kernel running, not SM occupancy, so 100% can still be starved; check true SM activity (dmonsm%/ DCGMSM_ACTIVE) - the first 60 seconds on an unfamiliar Linux host (the triage checklist)
- before you reach for
perf/flamegraphs — USE first tells you which resource is worth profiling
What ships with it
6 files 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.
- 4d ago First seen · 241 lines · 163 tokens per session scan A 974466d8a970
brendan is a skill published in the GitHub repository drubinstein/terry (1 stars, last pushed 2mo ago), licensed MIT. It adds 163 tokens to every session and 3,583 once invoked, about $0.0008 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
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
vertical-hr-recruiting
Domain-knowledge primer for the HR & recruiting vertical (ATS, onboarding, workforce scheduling, engagement). Applied by architect/pm during spec authoring so they aren't naive about hiring pipelines, the admitted offer→onboard data-carry gap, EEO/I-9 compliance, and shift-coverage rules. Stops the four products from…
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
vertical-retail
Retail & e-commerce domain knowledge for SMB storefront products (storefront, inventory, pricing, cart-recovery). Codifies the vocabulary (SKU vs variant, reorder point, COGS/margin, ATS, AOV), the non-obvious rules (Shopify owns the storefront — don't fight it head-on; the wedge is multichannel inventory + reorder…
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.