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 tu11aa/squadrant --skill where-i-amgit clone --depth 1 https://github.com/tu11aa/squadrantWrote 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/tu11aa/squadrant/where-i-am)<a href="https://agentmods.dev/skills/tu11aa/squadrant/where-i-am"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/where-i-am/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/tu11aa/squadrant/where-i-am"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/where-i-am.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00080 | $0.01249 |
| Opus 5.5 | $0.00032 | $0.00500 |
| Sonnet 5.5 | $0.00016 | $0.00250 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
where-i-am 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 21d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Where I Am
Answer "where am I on this project?" in a short, scannable report instead of a wall of text. Built for switching between long-running projects without losing the thread.
Read-only. This skill writes nothing and consumes nothing — pure orientation.
Output shape
Open with a one-line punchline, then the four sections in order:
**Right now →** <what you're actively doing / waiting on this moment, and your immediate next move>
## ✅ Done — and what it means
- <completed work> → <why it matters / what it unblocks>
## ⏳ In progress
- <work actively moving> — <state / owner: crew fixing, waiting on CI, mid-refactor>
## ▶️ Next
- ⬜ <the next not-yet-started step(s)>
## ⚠️ Watch
- <blockers, fragile state, gotchas, "don't forget", contradictions between sources>
Status markers — use inline when listing the steps of a track: ✅ done · ⏳ in progress · ⬜ not started.
Rules for the report:
Right now →is the most important line — the fast-orientation cue. Always include it; one line.- Bullets, not paragraphs. A handful per section, most-relevant first.
- Each Done bullet pairs what happened with why it matters (
→). A commit without significance is noise. - In progress vs Next: ⏳ is work already moving (a crew is on it, a branch is open, you're mid-edit); ⬜ Next is not yet started. Don't conflate them — the whole point is knowing what's live vs queued.
- Multi-track projects (e.g. a feature track + a bugfix track running in parallel): group bullets under bold track labels (
**Reorg track:**,**Bug-fix track:**) inside the sections. - If a section is genuinely empty, write
- — nothingrather than padding. - Synthesize, don't dump. Never paste raw git log / observation lists — distill them.
Source priority (current → durable)
Lead with the live session; use durable sources to fill gaps and cross-check.
- Current session context — primary. What this conversation has done, decided, and left open. Freshest signal, especially mid-task.
- claude-mem recent observations — the narrative across prior sessions (use the
mem-searchskill, or the recent-context already injected at session start). - Handoff + latest daily-log — explicit
nextSteps/blockedItems/decisionsandTomorrow/Blocked. - git — ground truth of where the code actually sits.
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.
- 21d ago Changed fd10066a6964
- 2mo ago First seen · 103 lines · 80 tokens per session scan A 787f4934e79c
where-i-am is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,249 once invoked, about $0.0003 per session on Opus 5.5. 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.
where-i-am compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| where-i-amtu11aa/squadrant | Skill | 2 | yesterday | MIT | A | 80 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |