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 petar-djukic/writing-skills --skill reverse-outlinegit clone --depth 1 https://github.com/petar-djukic/writing-skillsWrote 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/petar-djukic/writing-skills/reverse-outline)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/reverse-outline"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/reverse-outline/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/petar-djukic/writing-skills/reverse-outline"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/reverse-outline.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 | $0.00000 | $0.02798 |
| Opus 5 | $0.00000 | $0.01399 |
| Sonnet 5 | $0.00000 | $0.00560 |
| Haiku 4.5 | $0.00000 | $0.00280 |
Grade A, and why
reverse-outline 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 6d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: reverse-outline description: >- Decompose an article into its argument structure, persist that structure as HTML-comment markers in the text, and rank every paragraph and section by what the argument loses if it is cut. RST nuclearity at paragraph grain run as a reverse outline: one line per paragraph saying what it does for which other paragraph, then a deletion sheet ordered by distance from the point. Also re-checks each paragraph against its own marker after a rewrite pass, which is how compression damage becomes visible. Never rewrites prose. Triggers: reverse outline, decompose the argument, what can I cut, rank paragraphs, rst map, does this section earn its place, erosion check. argument-hint: 'Path to the markdown article, plus one of: annotate | rank | audit | strip'
reverse-outline
Answers one question the other instruments cannot: what does this section say that an earlier one did not?
Every existing tool works on a unit smaller than the problem. tighten-style
tightens sentences. critic-panel nominates one paragraph per critic. The
polemic blueprint budgets one structure in one form. AI-drafted text goes on
at the section as readily as at the sentence, and nothing asks a section to
justify its existence.
This skill labels the argument, then ranks by what deletion would cost. The author cuts from the bottom. No prose is written, at any point, which is why it can run after the terminal stage that forbids a generative pass.
Method
Three published pieces, one procedure.
- Reverse outlining (writing-centre practice; the Waterloo handout) is the procedure: write one sentence per paragraph saying what it does, then read the sentences against the thesis and look for repetition, drift, and gaps. Done by hand it works and nobody does it, because it is tedious at article length and has to be redone after every revision.
- Rhetorical Structure Theory (Mann & Thompson 1988) is the labelling. Spans join in pairs: a nucleus the author's purpose depends on, and a satellite supporting it. The definitional test is deletion — remove a satellite and the text still makes its point; remove a nucleus and it does not. RST's relation set is closed and each relation states its intended effect on the reader, which is exactly the "why is this paragraph here" line a reverse outline asks for.
- Marcu (1997) is the ranking: units ordered by nuclearity depth match what human summarizers keep. Read backwards, that is a deletion order.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed · +3 lines e3f6bf3303d3
- 11d ago First seen · 252 lines · 0 tokens per session scan A 1a52682192cb
reverse-outline is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,798 tokens. 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
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
structural-humanizer
Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.