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 jimmc414/claude-code-plugin-marketplace --skill write-docstring-firstgit clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplaceWrote 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/jimmc414/claude-code-plugin-marketplace/write-docstring-first)<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/write-docstring-first"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/write-docstring-first/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/jimmc414/claude-code-plugin-marketplace/write-docstring-first"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/write-docstring-first.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 | $0.00031 | $0.00627 |
| Opus 5.5 | $0.00012 | $0.00251 |
| Sonnet 5.5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
write-docstring-first 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-docstring-first
When to Use
- Writing any new function
- When clarity of purpose matters
- Complex logic that needs explanation
- Functions that will be reused
- Teaching or educational code
When NOT to Use
- Trivial one-liners (
return x + 1) - Private implementation details
- Rapidly prototyping (add later)
The Pattern
Docstring Fixpoint Theory: Iterate between docstring and code until they are isomorphic - each reads like a translation of the other.
# Step 1: Write docstring as specification
def rainfall(numbers):
"""Return the mean of the non-negative values in a list,
up to the first -999 (if it shows up)."""
...
# Step 2: Write code that mirrors the docstring
def rainfall(numbers):
"""Return the mean of the non-negative values in a list,
up to the first -999 (if it shows up)."""
return mean(non_negative(upto(-999, numbers)))
# Notice: docstring and code are almost the same sentence!
Example (from pytudes DocstringFixpoint.ipynb)
# The Rainfall Problem - evolved through fixpoint iteration
# Version 1: Problem statement as docstring
def rainfall(numbers):
"""Design a program called rainfall that consumes a list of numbers
representing daily rainfall amounts. The list may contain -999
indicating end of data. Produce the average of non-negative values
up to the first -999."""
...
# Version 2: Simplified docstring
def rainfall(numbers):
"""Produce the average of the non-negative values in a list,
up to the first -999 (if it shows up)."""
...
# Version 3: Code mirrors docstring
def rainfall(numbers):
"""Return the mean of the non-negative values in a list,
up to the first -999 (if it shows up)."""
return mean(non_negative(upto(-999, numbers)))
# Helper functions (each with its own fixpoint)
def upto(sentinel, items):
"""Return items that appear before sentinel,
or all items if sentinel doesn't appear."""
return items[:items.index(sentinel)] if sentinel in items else items
def non_negative(numbers):
"""The numbers that are >= 0."""
return [x for x in numbers if x >= 0]
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.
- 1mo ago First seen · 82 lines · 31 tokens per session scan A dc984034c87c
write-docstring-first is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 627 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
extract-ssot
Deduplicate repeated markdown (rule files, skill bodies, ADRs, docs) into one named source of truth and migrate every call site to cite it by exact heading. Use when the same prose, literal, or concept recurs across files: 'DRY this prose', 'extract a shared rule', 'single source of truth for X', a value-bump diff…
audit-encapsulation
Audit skill-encapsulation violations; remediation runs only behind an explicit fix FILE:LINE. External citations reaching into private surfaces inside .claude/skills/X/ or plugins/PLUGIN/skills/X/ (marketplace monorepos) beyond the slash invocation. Use when: 'audit encapsulation', 'find skill leaks', 'skill boundary…
generate
Build a source-backed AI industry briefing from official vendor publications, configured RSS feeds, GitHub releases, reputable secondary reporting, and user-supplied URLs. Use when: 'ai briefing', 'ai news', 'what's new in AI', 'catch me up on AI', 'prep for AI meeting', 'AI roundup', or 'generate AI slides'.
audit-progressive-disclosure
Read-only progressive-disclosure audit of agent-facing instruction markdown: grades each file against always-loaded, invocation-loaded, and on-demand tiers and flags split and disclosure defects. Use when: 'progressive disclosure', 'split this file', 'this file is too long', 'too much context', 'mixed concerns', 'hub…
firecrawl
Scrape, search, crawl, map, parse, or interact with web pages via the firecrawl-cli binary, writing results to disk instead of streaming them into context. Actions: scrape, search, crawl, map, parse, interact, agent, monitor, developer, research, doctor, search-feedback, credit-usage. Use when: 'scrape this page'…
quiz-me
Post-work comprehension check: a self-contained HTML report of a completed change (context, intuition, decisions) with a quiz at the bottom that tests the human, not the artifact; also recalls prior quizzed work. Non-gating by default; the quizpolicy userConfig tunes offer cadence. Use when the user says 'quiz me'…