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 capture-state-closuregit 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/capture-state-closure)<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/capture-state-closure"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/capture-state-closure/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/capture-state-closure"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/capture-state-closure.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 | $0.00027 | $0.00591 |
| Opus 5 | $0.00014 | $0.00296 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
capture-state-closure 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
capture-state-closure
When to Use
- Need state that persists across function calls
- Simpler than defining a class
- Creating specialized functions from a template
- Memoization with accessible cache
- Callback factories
When NOT to Use
- Multiple methods needed (use class)
- State is complex (use class)
- Need inheritance or protocols
The Pattern
Nested function captures variables from enclosing scope.
def make_counter(start=0):
"""Create a counter function with persistent state."""
count = start # Captured by inner function
def counter():
nonlocal count
count += 1
return count
return counter
c = make_counter(10)
c() # 11
c() # 12
Example (from pytudes)
# Memoization via closure (ngrams.py)
def memo(f):
"""Memoize function f."""
table = {} # Captured mutable state
def fmemo(*args):
if args not in table:
table[args] = f(*args)
return table[args]
fmemo.memo = table # Expose cache for inspection
return fmemo
@memo
def fibonacci(n):
if n <= 1:
return n
return fibonacci(n-1) + fibonacci(n-2)
# Access the cache
fibonacci.memo # {(0,): 0, (1,): 1, (2,): 1, ...}
# Symbol interning (lispy.py)
def Sym(s, symbol_table={}): # Mutable default = persistent state
"""Find or create unique Symbol for string s."""
if s not in symbol_table:
symbol_table[s] = Symbol(s)
return symbol_table[s]
# Same symbol every time
assert Sym('quote') is Sym('quote')
# Partial application via closure
def make_multiplier(factor):
"""Create a function that multiplies by factor."""
def multiply(x):
return x * factor # factor captured
return multiply
double = make_multiplier(2)
triple = make_multiplier(3)
double(5) # 10
triple(5) # 15
Key Principles
- Inner function sees outer scope: Variables are captured
- Mutable objects shared: Lists, dicts can be modified
- nonlocal for rebinding: Needed to reassign immutable captured vars
- Default args persist: Mutable default arg is like static variable
- Expose internals: Attach captured state as attribute for inspection
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.
- 9d ago First seen · 95 lines · 27 tokens per session scan A bc012889bedf
capture-state-closure is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 591 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
audit-progressive-disclosure
Read-only progressive-disclosure audit for agent-facing instruction markdown. Grades every target against a three-tier load-cost model (always-loaded / invocation-loaded / on-demand) and classifies seven finding shapes in two lanes: split opportunities (oversize vs tier-calibrated Anthropic-prescribed caps…
quiz-me
Post-work comprehension check: after a change is complete, generate a self-contained HTML report of what was done (context, intuition, decisions) with a quiz at the bottom that you answer. Verifying the HUMAN absorbed the work, not the artifact. Non-gating by default; the quizpolicy userConfig tunes offer cadence.…
reach
Run a Claude Code agent turn on ANOTHER machine in the fleet, over SSH on the tailnet. Every machine signs into its own Claude account, so the peer tools (ListAgents, SendMessage) are same-account and never span machines; SSH plus a headless claude -p is the path that does. Carries: resolving a target host from…
shape
Shape the assistant's output for a reader with ADHD, and anyone who wants action-first, low-friction responses. Lead with the concrete next action, number multi-step work, restate state across turns, cap and rank lists, give concrete time estimates, make wins visible, and cut preamble, recap, and closers. Use when…
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'.
changelog
Ingest Claude Code changelog entries and integrate them into the current repo. Fetch (read-only display), diff (impact analysis, no edits), status (applied versions), and apply (full integrate pipeline, explicit user intent only). Use when: 'new cc version', 'what changed in claude code', 'apply changelog', a new CC…