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 griffinwork40/agent-afk --skill orientgit clone --depth 1 https://github.com/griffinwork40/agent-afkWrote 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/griffinwork40/agent-afk/orient)<a href="https://agentmods.dev/skills/griffinwork40/agent-afk/orient"><img src="https://agentmods.dev/badge/skills/griffinwork40/agent-afk/orient/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/griffinwork40/agent-afk/orient"><img src="https://agentmods.dev/badge/skills/griffinwork40/agent-afk/orient.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 | $0.00057 | $0.00500 |
| Opus 5 | $0.00028 | $0.00250 |
| Sonnet 5 | $0.00011 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade B, and why
orient scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Memory: the **`memory_search` tool** (2–3 keyword queries on the current work; FTS5 syntax) + hot memory at `~/.afk/state/memory/HOT.md`. Do **not** grep `~/.claude/projects/**/memory/` — that path is vestigial and emp What it actually says
Sub-agent contract
/contract
Dispatch one read-only research sub-agent to survey recent work across four narrow targets, then produce a single markdown prompt block the user can paste into a fresh session.
Sub-agent surveys:
- Memory: the
memory_searchtool (2–3 keyword queries on the current work; FTS5 syntax) + hot memory at~/.afk/state/memory/HOT.md. Do not grep~/.claude/projects/**/memory/— that path is vestigial and empty on both trees; the archive is SQLite and onlymemory_searchreaches it. Report which stores you consulted. - Git activity in this repo + sibling repos the session touched (
git log --oneline -10, open PRs, dirty state) experiments/docs (if present) relevant to the current work- Telemetry/state files the session interacted with (e.g.
~/.afk/agent-framework/*.jsonl)
Return exactly this shape (≤ 60 lines total):
- One-line project identity + one-line "where we are" (current phase / latest milestone)
- 3–5 bullets on what shipped recently — commits, PRs, empirical closures; be specific
- Memory pointers by filename only (next session's memory system auto-loads — don't restate)
- 2–4 candidate directions framed as questions or possibilities, never as a decided plan
- Closing line inviting the next session to run
/ground-statefirst, then propose a plan
Discipline the contract enforces: orientation, not execution. Handoff briefs drift toward prescription by default; the "questions-as-possibilities" framing is the guardrail so the receiving session plans with fresh judgment.
Relay the prompt to the user. On request, save to /tmp/orient-<ISO8601>.md.
Skip when: no substantive work to carry forward, user wants a bare /compact, or user already has a decided plan (use /mint or draft directly).
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.
- yesterday First seen · 30 lines · 57 tokens per session scan B decf46404d29
orient is a skill published in the GitHub repository griffinwork40/agent-afk (53 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 500 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
capabilities
Your capability catalog — read this at boot. Lists the temporal date-range skills and the external integrations (reached via the loopback broker) available to you as a spawned worker, and exactly how to call each. Read-only. Consult it whenever you're unsure what tools/integrations you have or how to invoke them.
temporal
Resolve ANY named time window — today, yesterday, thisWeek, lastWeek, last7Days, last30Days, last90Days, thisMonth, lastMonth, thisQuarter, lastQuarter, thisYear, lastYear, last12Months — or an arbitrary range (lastNdays / lastNweeks / lastNmonths) to a concrete ISO date range relative to your run time. Read-only: no…
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
thisQuarter
Resolve "thisQuarter" to a concrete ISO date range relative to your run time — this quarter so far (quarter start → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a quarter-to-date task (QTD…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…