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 stitch-flowgit 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/stitch-flow)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/stitch-flow"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/stitch-flow/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/stitch-flow"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/stitch-flow.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 | $0.01461 |
| Opus 5.5 | $0.00000 | $0.00584 |
| Sonnet 5.5 | $0.00000 | $0.00292 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
stitch-flow 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 7d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: stitch-flow description: >- Repair discourse flow across paragraph boundaries after say-per-paragraph drafting: locate joints where a paragraph opens with a freestanding thesis instead of taking a handoff from the previous paragraph's close, then rewrite openings only — theme of the opener drawn from the rheme of the paragraph before, duplicate definitions merged, rhythm varied — leaving claims, citations, anchors, and rst markers untouched. Ships openers.py, which prints each section's joint chain with weak-joint and duplicate-definition flags. Triggers: stitch the flow, the paragraphs don't flow, written paragraph by paragraph, doesn't read as one piece, weak joints, paragraph openers, given-new. argument-hint: '<chapter.md> [...] (detection); then the stitch pass by hand'
Stitch Flow (discourse joints between paragraphs)
The failure this fixes
SRD-first drafting writes one say per paragraph, and each say is written to be complete in itself. The result reads correct and does not flow: nearly every paragraph opens with a freestanding thesis sentence ("An agent is a generic runtime." / "A role is a specification." / "Switching roles costs no release."), takes no handoff from the paragraph before it, and could be shuffled without breaking the text. Secondary symptoms of the same cause: uniform paragraph rhythm (definition, elaboration, consequence, three to five sentences, every time), section cross-references doing the work transitions should ("the previous section's sense"), and the same thing defined twice because each paragraph re-establishes its own context.
The failure has shipped twice (agent-dsl; autogenic-systems roles-and-teams) because every existing gate reads one paragraph at a time. reverse-outline checks that each satellite serves its section's nucleus — logical coherence, not flow. tighten-style TS-10/TS-11 govern the spine inside a paragraph, and its rewriter refuses to add transitions by contract. Critic panels see passages. And match-structure's paragraph_cohesion metric — tf-idf overlap between consecutive paragraphs — scores the disease higher than the cure: the roles-and-teams article measured 0.16 against 0.08-0.12 for its venue exemplars, because re-establishing the same nouns in every paragraph is exactly what the metric rewards. Do not gate this skill on that number.
What ships with it
2 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.
- 7d ago First seen · 128 lines · 0 tokens per session scan A 0e5a5825ed94
stitch-flow is a skill published in the GitHub repository petar-djukic/writing-skills (5 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,461 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 2026-10-09.
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-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-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.
story-setup
A setup tool for deploying a Chinese web-fiction writing toolkit into a project. It configures supported coding agents and uses shared files for environments without a dedicated integration.
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.