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 skills add glebis/claude-skills --skill pre-session-portraitgit clone --depth 1 https://github.com/glebis/claude-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/glebis/claude-skills/pre-session-portrait)<a href="https://agentmods.dev/skills/glebis/claude-skills/pre-session-portrait"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/pre-session-portrait/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/glebis/claude-skills/pre-session-portrait"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/pre-session-portrait.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00160 | $0.01490 |
| Opus 5 | $0.00080 | $0.00745 |
| Sonnet 5 | $0.00032 | $0.00298 |
| Haiku 4.5 | $0.00016 | $0.00149 |
Grade A, and why
pre-session-portrait 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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Session Portrait
Turn "help me with X" into a decision-grade brief before the session starts. The instrument asks the client open, voice-note-friendly questions across seven fixed lenses; the consultant (or an LLM) compresses each answer to one line, yielding a portrait that is iterable, compressible, and easy to visualize.
Design principle: rich in, compressed out. The client talks freely; compression happens after, not in their head.
The seven lenses
| # | Lens | Elicits | Compresses to |
|---|---|---|---|
| 0 | ANCHOR | the topic — what the call is for (referent for every later "this") | the topic in one line |
| 1 | WHERE | what's been tried, where it stalls | current state in one line |
| 2 | HOW | cognitive style — fast/slow, visual/verbal, systems/stories | how they think |
| 3 | WHAT | live preoccupations, open loops | current focus |
| 4 | PROBLEM | the problem under the problem | the core job |
| 5 | IDEAL | concrete "solved" state (day/feeling, not tool) | desired outcome |
| 6 | TENSION | what holds them back / worries them | dominant anxiety |
| 7 | JTBD | Push · Pull · Habit · Anxiety · Trigger | switching forces |
Output schema
portrait:
where: ""
how: ""
what: ""
problem: ""
ideal: ""
tension: ""
jtbd:
push: ""
pull: ""
habit: ""
anxiety: ""
trigger: ""
How it visualizes
- 7-spoke radial / hexad map — one label per lens, the capture line as the value.
- JTBD 2×2 — Push+Pull (energy toward change) vs Habit+Anxiety (energy against). The gap = leverage.
- Iterable — re-run any lens next session; watch the capture line drift over time.
Workflow
- Gather context. Client name, consultant name, session date, and (if known) the topic. Pull prior history from vault/email/Fathom if available so the consultant-only prep notes are grounded.
- Fill the template. Copy
assets/interview-prompt.mdand substitute{{CONSULTANT}}(and topic if narrowing lens 4). Leave the seven lenses intact. - Pick a delivery (ask the user):
- Raw text — paste the substituted prompt into a message; client runs it in any clean Claude/ChatGPT.
- Secret gist —
gh gist create --desc "Pre-session portrait interview (for <name>)" interview-prompt.md. Share the gist link. Use the unpinned raw URL (/raw/<filename>) so edits propagate. - Codex one-liner — see
assets/codex-bootstrap.txt; fetches the raw gist URL and runs the interview interactively.
- Optional preview. Before sending, generate a synthetic filled-in version (answers simulated from known context) so the consultant judges the deliverable's shape. Mark it clearly as synthetic.
- After the session. Fold the returned
portrait:YAML into the client's People/Session note; diff against any prior portrait to show movement.
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.
- 8d ago First seen · 81 lines · 0 tokens per session scan A a8e520dd30fb
pre-session-portrait is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 160 tokens to every session and 1,490 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 2026-09-03.
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…