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 validate-before-processgit 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/validate-before-process)<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/validate-before-process"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/validate-before-process/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/validate-before-process"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/validate-before-process.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 | $0.00024 | $0.00696 |
| Opus 5.5 | $0.00010 | $0.00278 |
| Sonnet 5.5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
validate-before-process 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
validate-before-process
When to Use
- Accepting external/user input
- File format must be exact
- Early failure is better than silent corruption
- Building robust parsers
When NOT to Use
- Trusted internal data
- Validation overhead too high
- Best-effort processing is acceptable
The Pattern
Validate input structure before processing, with clear error messages.
def parse_grid(grid_string):
"""Parse and validate a grid."""
lines = grid_string.strip().split('\n')
# Validate structure
if not lines:
raise ValueError("Empty grid")
width = len(lines[0])
for i, line in enumerate(lines):
if len(line) != width:
raise ValueError(f"Line {i} has wrong width: {len(line)} != {width}")
# Now safe to process
return [[c for c in line] for line in lines]
def validate(data, predicate, message):
"""Validate data with predicate, raise with message if fails."""
if not predicate(data):
raise ValueError(f"{message}: {data}")
return data
Example (from pytudes)
# Grid validation (sudoku.py)
def grid_values(grid):
"""Convert grid into a dict of {square: char}."""
chars = [c for c in grid if c in digits or c in '0.']
# Validate length
if len(chars) != 81:
print(grid, chars, len(chars))
assert len(chars) == 81, f"Expected 81 chars, got {len(chars)}"
return dict(zip(squares, chars))
# Formula validation (Cryptarithmetic.ipynb)
def valid(pformula):
"""A formula is valid iff it has no leading zero and evaluates to True."""
try:
return (not leading_zero(pformula)) and (eval(pformula) is True)
except ArithmeticError:
return False
leading_zero = re.compile(r'\b0[0-9]').search
# Number of letters check
def translate_formula(formula):
letters = all_letters(formula)
assert len(letters) <= 10, f'{len(letters)} letters is too many; only 10 allowed'
...
# Lispy require function (lispy.py)
def require(x, predicate, msg="wrong length"):
"""Signal a syntax error if predicate is false."""
if not predicate:
raise SyntaxError(to_string(x) + ': ' + msg)
# Usage in parsing
def expand(x):
require(x, x != []) # Empty list is error
if x[0] is _quote:
require(x, len(x) == 2) # quote needs exactly 2 elements
return x
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 · 98 lines · 24 tokens per session scan A 1d93fae09bb8
validate-before-process is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 696 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
audit-dead-code
Read-only hunt for dead and unused code across four labeled lanes (Knip for TS/JS, vulture for Python, gopls for Go, grep for shell and files no lane owns), each candidate adjudicated dead, uncertain or alive. Use when asked to 'find dead code', to find what is unused in a repository (exports, functions, orphaned…
devils-advocate
Stress-test plans and proposals via systematic adversarial review. Assumption extraction, evidence check, failure scenarios, operational gotchas. Before implementation begins. Use when: asked to attack a plan or proposal ('devil's advocate', 'stress test', 'poke holes', 'what could go wrong'), or before implementation…
known-issues
Lookup and tracking of known Claude product issues: GitHub bug search, service health and model quality checks, and a persistent registry of tracked issues. Use when: 'is this broken', 'any workarounds', 'troubleshoot Claude Code', 'feature behaves unexpectedly', 'scan repo for issues', 'file a bug'. Actions: status…
target
Identify and rank optimization targets by evidence quality, so an unmeasured system yields 'instrument this first' instead of a guess. Accepts session pain, a named path, telemetry, or open-ended 'what is slow here'. Use when: 'what should we optimize', 'find the bottleneck', 'this feels slow', 'is X worth…
diagnose
Diagnose unexpected behavior from Claude Code's built-in computer-use MCP server (desktop screen control). Use when: 'computer use', 'control my screen', 'screenshot is blurry', 'why is the screenshot low resolution', 'zoom in on the screen', 'screenshot capture failed', 'empty capture', 'clicks are landing in the…
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…