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/jlevy/repren/flowmarknpx skills add jlevy/repren --skill flowmarkgit clone --depth 1 https://github.com/jlevy/reprenWhat 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 | $0.00064 | $0.00626 |
| Opus 5 | $0.00032 | $0.00313 |
| Sonnet 5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
flowmark 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flowmark - Markdown Auto-Formatter
Fast, consistent Markdown auto-formatter. Run it on Markdown you generate or edit so committed diffs stay small and readable. It is conservative and safe to run on every file: it never modifies code blocks or inline code.
Format Markdown
Format in place with all auto-formatting (typography, cleanups, semantic line breaks):
flowmark --auto FILE # one file
flowmark --auto . # whole tree (respects .gitignore and .flowmarkignore)
Omit --auto to preview to stdout; pipe stdin with - (e.g. cat FILE | flowmark -).
Use flowmark when it is already on PATH. Otherwise use the fast
Rust port with a version-pinned uvx runner
(never @latest):
uvx --from flowmark-rs==0.3.2 flowmark --auto FILE
The Python reference remains available when its library API or a newer unported patch is required:
uvx --from flowmark==0.7.3 flowmark --auto FILE
Adopt Flowmark in a Repository
If this skill came from flowmark --skill, run the same runner with --install-skill
from the project root to materialize the complete bundle.
Then, for a repository-wide migration, Makefile wiring, .flowmarkignore, commit hooks,
CI policy, and disabling Prettier or other competing Markdown formatters, read
project-setup.md in full before editing.
Full Documentation
Flowmark documents itself. Use the CLI rather than reproducing details here:
flowmark --help— every flag:--semantic,--smartquotes,--ellipses,--width,--check, list spacing, and file discovery (--extend-include/--extend-exclude).flowmark --docs— the full guide: configuration, file discovery, editor setup, the Python library API, and installing this skill (flowmark --install-skill).
What ships with it
1 file 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.
- yesterday First seen · 63 lines · 64 tokens per session scan A 02aedf69dfa1
flowmark is a skill published in the GitHub repository jlevy/repren (374 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 626 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
refactor
Refactor code to improve structure and maintainability.
code-simplifier
Simplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.
arch-optimize
架构优化技能 v3.2：六大衰退风险扫描（R1-R6）、质量度量（MI/CC/健康分）、回归防护。五阶段工作流配 4 个零依赖本地脚本（archscan/depgraph/riskdiagnose/qualitymetrics/regressionguard），全部输出 JSON。在架构审查、技术债评估、代码重构、质量提升、工程结构评审时调用。.
migrate-rename
Evolutionary file renaming with wrapper files. Enables renames without hard breaks — references are organically updated through usage.
code-simplifier
Simplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.
pipeline-optimizer
Structured 6-step procedure for improving, renovating, or rebuilding existing pipelines, individual project folders, documentation structures, or software stacks. Addressable as "pipeline optimizer" (for whole topic pipelines, e.g. a software, research, or game-dev pipeline) or "project-folder optimizer" (for…