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 agentmods add skills/outlinedriven/odin-gemini-cli-extension/edit-articlenpx skills add OutlineDriven/odin-gemini-cli-extension --skill edit-articlegit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/edit-article)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/edit-article"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/edit-article.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.00828 |
| Opus 5 | $0.00030 | $0.00414 |
| Sonnet 5 | $0.00012 | $0.00166 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
edit-article 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 5d 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.
This is a copy
100% identical to edit-article — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mechanical, structural-only edits to prose. Voice and register are load-bearing and preserved verbatim.
Allowed transformations
- Restructure section order to respect information dependencies (treat info as a DAG; later sections may depend on earlier, never vice versa).
- Split a paragraph carrying two distinct points into two paragraphs.
- Merge two short paragraphs that carry the same point into one.
- Remove redundant sentences, clauses, or words that repeat what was already stated.
- Consolidate parallel lists or tables into a single canonical form when content overlaps.
- Tighten run-on sentences into shorter, clearer ones — preserving the original meaning and the original word choice where possible.
- Cap paragraphs at ~240 characters where doing so requires no rephrasing.
- Promote inline asides into footnotes or sidebars when they break flow.
- Demote redundant headings; promote orphan paragraphs to their own subsection.
Forbidden transformations (hard fence)
- Do NOT change voice (active/passive, first/second/third person).
- Do NOT change register (formal ↔ casual).
- Do NOT change tone (technical, decision-oriented, imperative).
- Do NOT rewrite ODIN-mandated phrasing — terse imperative, third-person, English-mandate, decision-first prose stays.
- Do NOT introduce new claims, examples, or analogies that were not in the source.
- Do NOT remove technical specificity (file paths, command flags, version numbers, named constants).
- Do NOT rename headers, fields, or list items even if they look redundant — those are structural and load-bearing.
- Do NOT translate non-English-mandate content into a different style "for clarity."
- Do NOT add emojis, gradients of warmth, marketing language, or hedging.
If a transformation seems necessary but lives in the forbidden list, STOP and surface the question to the user.
Protocol
- Dispatch Explore agent (or read directly for ≤50 LOC) to map the document into sections by heading. Build the dependency graph.
- Confirm the section order and graph with the user before any edit.
- For each section, in dependency order:
- Identify candidate transformations from the allowed list.
- Apply only those. Surface any forbidden-list candidates as questions.
- Diff with
difftafter the edit; reject the change if voice/register/tone shifted.
- After all sections are processed, re-read the document end-to-end. Confirm flow without re-editing.
- Commit with message:
docs: tighten <document-name> (mechanical edits only).
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.
- 5d ago First seen · 64 lines · 61 tokens per session scan A 96b8fd3e8fb2
edit-article is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 828 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to edit-article, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.