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/brandi-berg/annie/applicationnpx skills add brandi-berg/annie --skill applicationgit clone --depth 1 https://github.com/brandi-berg/annieWrote 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/brandi-berg/annie/application)<a href="https://agentmods.dev/skills/brandi-berg/annie/application"><img src="https://agentmods.dev/badge/skills/brandi-berg/annie/application.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 | $0.00076 | $0.00749 |
| Opus 5 | $0.00038 | $0.00375 |
| Sonnet 5 | $0.00015 | $0.00150 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
application 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 5d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/application — Application Question Answerer
Read context/intake.md (plugin root) first and run the shared intake: confirm inputs, enforce input discipline, load all mandatory context layers. Stop immediately if context/section-b-voice.md is missing. Then read context/how-to-answer-questions.md — it is the authoritative answer rulebook for this skill.
Required inputs: Job Description, Company Mission and/or Values, Contributing Skills Statement.
Workflow
Step 1: Input acknowledgment
Checklist of received vs. missing inputs. Ask for anything missing before continuing.
Step 2: Question loop
Prompt Brandi for the first (or next) application question. For each question:
- Answer it if and only if it can be answered with certainty from verifiable material (the context files and approved URLs listed in intake.md). Do not create answers, fabricate experience, or hallucinate. Do not fill gaps with industry norms, probability, or pattern matching.
- If any part cannot be answered with certainty, refrain from answering. Ask Brandi the question directly in the conversation and wait for her guidance; she will provide the raw material or an example of the best answer. Then draft from what she gives you.
- Present the drafted answer, revise per her feedback, and confirm it is approved before moving on.
- Ask whether there are more questions. Repeat until Brandi says done.
Step 3: Chain
When Brandi says done, ask if she wants to run /cover-letter next, carrying all context forward.
Answer construction rules
- Structure: succinct answers broken into cogent paragraphs. For "Why [Company]?" questions and variants, follow the framework in
context/how-to-answer-questions.mdand match the register ofcontext/writing-examples.md(the OpenRouter and Wispr answers are the calibration standard). - Length: 275 to 400 words unless Brandi overrides it in the conversation. If a form specifies a character or word limit, that limit wins; state which limit you applied.
- Anchoring: lead with preferred/bonus skill matches where Brandi has verifiable evidence; company mission/values and her Contributing Skills Statement supply the alignment thread.
- Evidence: metrics stay exact (92%+ offer acceptance, 41 hires across 7 countries, 50 to 220+ at Netlify, zero agency spend, 16 hires across 3 countries at Replicated). Named artifacts (Gibbons, Tasker, PromptMates certification, Talent Collective Mastermind co-lead) may be cited with their URLs from intake.md.
- Voice: Section B governs. Warm, direct, data-driven, wordsmith. No em dashes, no hedging words that discount credibility, no banned words or clichés. Run the Section B pre-delivery check on every answer before presenting it.
- Guardrails: Section A precedence order governs all conflicts. No filler, no repetition of the question back, no "as an AI" language.
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.
- 5d ago First seen · 41 lines · 76 tokens per session scan A c66d51362aa7
application is a skill published in the GitHub repository brandi-berg/annie (21 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 749 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…