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 EZotoff/ez-omo-config --skill reader-reportgit 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/skills/ezotoff/ez-omo-config/reader-report)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/reader-report"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/reader-report.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.07250 |
| Opus 5 | $0.00040 | $0.03625 |
| Sonnet 5 | $0.00016 | $0.01450 |
| Haiku 4.5 | $0.00008 | $0.00725 |
Grade A, and why
reader-report 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.
How it starts
The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reader-Report — Self-Contained, Reader-First Writing
The recurring failure this skill exists to fix: deliverables that read as if the reader has already read everything else. Symptoms include undefined acronyms and names, process-internal language ("carried over from v3", "inherited from your analysis"), comparative summaries ("X was discarded in favour of Y"), judge/block/score references the reader never saw, and prose that describes how the work was done instead of what the result is.
Your register is editorial, confident, and direct — not academic, not marketing.
When to use this skill
Load this skill whenever the deliverable is something a human reads to understand a result:
- HTML reports, dashboard copy, survey reports
- MD design documents, technical briefs, executive summaries
- Debate / panel-review / decision-review result summaries
- Handoff notes, post-mortems, pre-mortems, red-team reports
- Any artifact where a reader's job is to learn what was decided / found / recommended
When NOT to use this skill
- Bug reports, incident reports, status updates, telemetry, logging
- Code comments, commit messages, PR descriptions (those have their own conventions)
- Ordinary chat answers to a question
- The raw audit record (judge outputs, transcripts, scoring YAML) — those are for traceability, not reading
The reader contract (non-negotiable)
These hold for every reader-facing surface. Violating any of them breaks the contract.
1. Lead with the answer
The decision, recommendation, or finding comes first — before any background, methodology, or context. A reader who stops after the first paragraph must have the outcome.
Bad: "Three judges evaluated the proposal across correctness, feasibility, and risk. The analyst scored block b1 at 4/5…" Good: "Adopt the proposal. It solves the stated problem, is feasible with current resources, and the main risk (X) has a documented fallback."
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.
- 4d ago Changed · +102 lines 633e89dac672
- 8d ago First seen · 258 lines · 80 tokens per session scan A dad3571b6673
reader-report is a skill published in the GitHub repository EZotoff/ez-omo-config (5 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 7,250 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.
Other skills, from other repositories
omc-plan
Strategic planning with optional interview workflow.
launch
Shipyard's governed delivery pipeline — converge the mission, synthesize a durable spec, decompose vertical-slice tickets with blocking edges, run the frontier in parallel via team, close with verification, and report with a full decision log. Two entry gates — the yard gate (drydock audit) and the fog gate (an effort…
ralph
Self-referential loop until task completion with configurable verification reviewer.
self-improve
Autonomous evolutionary code improvement engine with tournament selection.
autopilot
Full autonomous execution from idea to working code.
drydock
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check…