profile

profile is a skill for Claude Code, Codex from WinterDDo/claude-code-skill-autopilot. It costs 79 tokens per session (477 once invoked), scanned A, original, MIT.

A dashboard for reviewing what Skill Autopilot has done, what it has learned, and which commands or skills you use.

In plain words
What is it for?
Use it to inspect activity counts, compare earlier and recent command use, review learned rules, and draft feedback.
Why use it?
It makes the autopilot's suggestions, learned rules, and changes in your working habits visible instead of hidden.

Skill for Claude CodeCodex

Part of the skill-autopilot plugin — 6 skills, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/winterddo/claude-code-skill-autopilot/profile
Any agent
npx skills add WinterDDo/claude-code-skill-autopilot --skill profile
Clone the repo
git clone --depth 1 https://github.com/WinterDDo/claude-code-skill-autopilot

Made for: Claude Code, Codex.

Or install skill-autopilot, the plugin that ships this one along with the rest of its 6 skills, 4 hooks.

Wrote 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.

agentmods badge for profile

README.md
[![agentmods](https://agentmods.dev/badge/skills/winterddo/claude-code-skill-autopilot/profile.svg)](https://agentmods.dev/skills/winterddo/claude-code-skill-autopilot/profile)
Your own site
<a href="https://agentmods.dev/skills/winterddo/claude-code-skill-autopilot/profile"><img src="https://agentmods.dev/badge/skills/winterddo/claude-code-skill-autopilot/profile.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.00477
Opus 5 $0.00039 $0.00238
Sonnet 5 $0.00016 $0.00095
Haiku 4.5 $0.00008 $0.00048

Measured 4d ago against content hash f6eba13482e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

profile 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.

plugins/skill-autopilot/skills/profile/SKILL.md · 26 lines

What it actually says

Autopilot dashboard

Every number MUST be traceable to a real entry in the data files. Never fabricate or extrapolate a value claim. If a number is zero, show zero.

Data sources

Read from ~/.claude/command-autopilot/: state.json (counters, milestones, config), events.jsonl + events-archive.jsonl (the ledger), learned.json (rules), skills-index.json.

Report (user's language, compact)

  1. Value ledger — counts from events: auto plan-mode entries, skills auto-invoked (top 3 by count, with names), suggestions accepted vs made. One line each, with the period covered.
  2. Before/after — compare the oldest 7 days of events against the newest 7 (only if ≥14 days of data; otherwise say "still collecting"): self-used commands per week then vs now. This is the user's own growth, shown from their own data.
  3. Learned rules — each in_force rule with its evidence count and last-confirmed date. If none: "still observing, first rules typically appear after ~10 sessions."
  4. Mastered — habits with self-use evidence; note that teaching for them has naturally stopped.
  5. Controls — one line: config skill to quiet/mute, evolve skill to re-distill, "delete rule N" works right here.

Feedback draft

If the user is dissatisfied with any suggestion behavior, offer to draft a GitHub issue for WinterDDo/claude-code-skill-autopilot: title, what happened, expected behavior, and (only with explicit consent) the relevant anonymized evidence lines. Show the draft; the user files it themselves.

Rule deletion

"Delete rule N" → remove it from learned.json, confirm in one line.

Changes

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.

  1. 4d ago First seen · 26 lines · 79 tokens per session scan A f6eba13482e7

Subscribe to this mod's changes

profile is a skill published in the GitHub repository WinterDDo/claude-code-skill-autopilot (6 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 477 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 2026-08-31.