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.
git clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/commands/ezotoff/ez-omo-config/episode)<a href="https://agentmods.dev/commands/ezotoff/ez-omo-config/episode"><img src="https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/episode/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/commands/ezotoff/ez-omo-config/episode"><img src="https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/episode.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 | $0.00011 | $0.00444 |
| Opus 5.5 | $0.00004 | $0.00178 |
| Sonnet 5.5 | $0.00002 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
episode 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 17d 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.
What it actually says
Record a checkpoint for the current episode by invoking the receipt script directly — this command documents the invocation; it does NOT pretend to observe the transcript.
Run from the episode's project root:
scripts/episode-receipt.sh append .omo/episodes/<slug> --checkpoint \
--intent "<what this session is doing for the episode>" \
--claims '["<what was done, as verifiable claims>"]' \
--evidence-refs "<paths + quoted message excerpts with message IDs, comma-separated>" \
--resume-pointer "<where the next session should pick up>"
Rules:
- Every argument must be explicit — the script does not infer intent, claims, or evidence from the session.
- Evidence refs MUST include quoted message excerpts with their message IDs (bounded
session_evidence); never paste full transcripts. A session-evidence ref has the exact formmsg:<message-id>|<quoted excerpt>(comma-separated with file refs; excerpts must not contain commas) — the receipt stores{path: "msg:<message-id>", sha256: <sha256 of excerpt UTF-8 bytes>, excerpt}, andverifyrecomputes the digest over the stored excerpt (mismatch → digest-mismatch failure). - If no manifest exists yet for the episode,
--checkpointauto-creates a minimal one at.omo/episodes/<slug>/manifest.yaml— the manifest is the single source of truth; no sidecar receipts. - Never fabricate a checkpoint: if you cannot name concrete evidence, say so and stop.
Then check episode hygiene with scripts/episode-receipt.sh lint .omo/episodes/<slug> (flags, never fixes):
- Stale active episodes: manifests with
status: activebut no activity (last verify or newest receipt) in >7 days — report them. - Missing checkpoints:
status: activewith nokind:"checkpoint"receipt — name the gap and checkpoint it now.
Reply with: the receipt sequence number (or the script's error), and any hygiene flags raised.
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.
- 17d ago First seen · 30 lines · 11 tokens per session scan A 589079c09b20
episode is a command published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 444 once invoked, about $0.0000 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 2026-09-29.
Other commands, from other repositories
deja
Search this machine's past AI coding sessions (deja-vu).
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
help
Explain Ralph Wiggum technique and available commands.
start
First-time onboarding — guided setup.