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/jamienpx skills add drubinstein/terry --skill jamiegit 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/jamie)<a href="https://agentmods.dev/skills/drubinstein/terry/jamie"><img src="https://agentmods.dev/badge/skills/drubinstein/terry/jamie.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 | $0.00131 | $0.03163 |
| Opus 5 | $0.00066 | $0.01581 |
| Sonnet 5 | $0.00026 | $0.00633 |
| Haiku 4.5 | $0.00013 | $0.00316 |
Grade A, and why
jamie 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jamie — replicate the report to confirm the bug
The claim · the rig · the verdict.
Jamie takes a bug report and tries to make it happen — on purpose, reliably — before anyone tries to fix it. A report is a claim, not a fact: "the app crashes when I upload a CSV" is a hypothesis until you can pull the trigger yourself. Jamie's job is to convert that claim into a minimal, reliable reproduction and stamp it with a verdict, Mythbusters-style:
- CONFIRMED — reproduced reliably; you hold a minimal, one-command repro (and a reliability rate if it's intermittent).
- PLAUSIBLE — reproduces only under conditions you had to discover, or a real adjacent defect exists but not the exact report.
- BUSTED — could not reproduce after faithfully recreating the conditions and escalating. Not "there's no bug" — "the report as written doesn't reproduce" — and you say why.
The whole discipline rests on one rule: a failed reproduction is evidence about a mismatched condition, not proof the reporter is wrong. Most "can't reproduce" is one unmatched variable — the wrong version, the wrong data, the wrong platform, the wrong timing — away from a perfect repro.
Six moves:
- The report is a claim. Turn the prose into a falsifiable statement: exact preconditions, steps, expected vs actual, and the environment it was seen in. Write down what the report doesn't say (the unstated conditions).
- Match their world, not yours. Recreate the version they hit (checkout that release/commit, not latest), their config/flags, their data/inputs, their platform/OS/arch, locale/timezone, account/permissions/state, concurrency/scale.
- Build the rig and capture the failure. Reproduce the full scenario until it fails, and capture the failure as an artifact (a log, a crash, a diff) — not "I think I saw it."
- Minimize. Shrink the working repro to the smallest thing that still fails (delete-and-retest). The deliverable is a repro someone else can run in one step.
- Quantify reliability. 100% or intermittent? Run it N times and report the rate (e.g. 7/20). Intermittent is a number, not a shrug.
- Never bust on the first miss. Before declaring BUSTED, escalate: vary the condition you most likely mismatched, ask the reporter for the one missing variable, and check whether it's already been fixed.
What ships with it
4 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 · 209 lines · 0 tokens per session scan A 1e345049d872
jamie is a skill published in the GitHub repository drubinstein/terry (1 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 3,163 once invoked, about $0.0007 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.