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 commands/romilly/claude-code-helpers/matchersgit clone --depth 1 https://github.com/romilly/claude-code-helpersWhat 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 | $0.00000 | $0.01585 |
| Opus 5 | $0.00000 | $0.00792 |
| Sonnet 5 | $0.00000 | $0.00317 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
matchers 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyHamcrest Custom Matchers Guide
When to Create a Custom Matcher
Create a custom matcher when:
- Multiple tests check the same object's properties
- You want clearer failure messages than plain assertions provide
Don't create a matcher for a one-off assertion - plain assert is fine.
Spotting Opportunities
Test smell: Length assertion followed by individual item checks:
# Before - verbose and redundant length check
assert len(tasks_node.children) == 2
assert tasks_node.children[0].id == "ID_1"
assert tasks_node.children[0].title == "Task A"
assert tasks_node.children[1].id == "ID_2"
assert tasks_node.children[1].title == "Task B"
# After - expressive, no length check needed
assert_that(tasks_node.children, contains_exactly(
node(id="ID_1", title="Task A"),
node(id="ID_2", title="Task B"),
))
The contains_exactly matcher handles "exactly these items, no more, no less" - eliminating the redundant length assertion.
Naming Convention
Name matcher functions after the type they match, without an is_ prefix:
node(...)notis_node(...)link(...)notis_link(...)
This reads naturally with contains_exactly: "contains exactly node with id X, node with id Y".
The Pattern
"""Custom PyHamcrest matchers for the test suite."""
from hamcrest.core.base_matcher import BaseMatcher
from hamcrest.core.description import Description
from myproject.domain import MyObject
class IsMyObjectMatcher(BaseMatcher):
"""Matcher for MyObject with optional property checks."""
def __init__(self, name: str | None = None, value: int | None = None):
self.expected_name = name
self.expected_value = value
def _matches(self, item) -> bool:
if not isinstance(item, MyObject):
return False
if self.expected_name is not None and item.name != self.expected_name:
return False
if self.expected_value is not None and item.value != self.expected_value:
return False
return True
def describe_to(self, description: Description) -> None:
parts = ["a MyObject"]
if self.expected_name is not None:
parts.append(f"with name={self.expected_name!r}")
if self.expected_value is not None:
parts.append(f"with value={self.expected_value}")
description.append_text(" ".join(parts))
def describe_mismatch(self, item, mismatch_description: Description) -> None:
if not isinstance(item, MyObject):
mismatch_description.append_text(f"was {type(item).__name__}")
elif self.expected_name is not None and item.name != self.expected_name:
mismatch_description.append_text(f"had name={item.name!r}")
elif self.expected_value is not None and item.value != self.expected_value:
mismatch_description.append_text(f"had value={item.value}")
def my_object(name: str | None = None, value: int | None = None):
"""Match a MyObject with optional property checks."""
return IsMyObjectMatcher(name=name, value=value)
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 · 216 lines · 0 tokens per session scan A 057a15e29dca
matchers is a command published in the GitHub repository romilly/claude-code-helpers (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,585 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.