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/reflexioai/claude-smart/check-and-testnpx skills add ReflexioAI/claude-smart --skill check-and-testgit clone --depth 1 https://github.com/ReflexioAI/claude-smartWhat 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 | $0.00097 | $0.01959 |
| Opus 5 | $0.00048 | $0.00979 |
| Sonnet 5 | $0.00019 | $0.00392 |
| Haiku 4.5 | $0.00010 | $0.00196 |
Grade A, and why
check-and-test 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- check-and-test — 98% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check and Test
Run the standard check-and-test flow (lint + type-check + pytest tiers), including tests normally skipped during pre-commit hooks.
Overview
This command runs the standard check-and-test tiers:
- Python lint checks via ruff (code quality, security, complexity)
- Python type checks via pyright (type safety)
- TypeScript/JavaScript lint checks via Biome (code quality, formatting, import sorting)
- TypeScript/JavaScript type checks via tsc (type safety)
- Unit tests in
reflexio/tests/(excluding e2e and tests under reflexio/tests/server/llm/) - E2E tests in
reflexio/tests/e2e_tests/(skip all the low priority test by NOT setting RUN_LOW_PRIORITY env variable) - Tests skipped during pre-commit (those decorated with
@skip_in_precommit)
The key difference from pre-commit is that PRECOMMIT env var is NOT set, so all tests run.
Prerequisites
Before running tests, activate the virtual environment:
source .venv/bin/activate
Test Execution
IMPORTANT: Run all tests sequentially using -n 0 to avoid test conflicts. The default pytest config uses parallel execution (-n auto), but this can cause race conditions and shared state issues between tests.
Step 0: Run Lint and Type Checks
Run lint and type checks across the full codebase before running tests.
0a. Ruff auto-fix:
ruff check --fix reflexio/
ruff format reflexio/
0b. Ruff remaining errors:
ruff check reflexio/
If any errors remain that ruff could not auto-fix, read each error, understand the issue, and fix the code yourself. Do NOT skip unfixed lint errors.
0c. Pyright type check:
pyright
Pyright uses pyrightconfig.json for scope. If any type errors are reported, read each error, understand the type issue, and fix the code yourself. Do NOT skip unfixed type errors.
0d. Biome auto-fix (TypeScript/JavaScript):
cd reflexio/website && npx biome check --write . && cd ../..
cd reflexio/public_docs && npx biome check --write . && cd ../..
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.
- 2d ago First seen · 229 lines · 97 tokens per session scan A 655a8c63a4ac
check-and-test is a skill published in the GitHub repository ReflexioAI/claude-smart (772 stars, last pushed 4d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,959 once invoked, about $0.0005 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
reflexio-embedded
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
reflexio-consolidate
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
reflexio
When to use: Always active. This skill is the contract between you and the reflexio cross-session memory plugin.
learn
When to use: The user wants immediate extraction of skills/preferences from the current session — e.g., after a major correction, before context compaction, or to test the loop.
clear-all
When to use: The user explicitly asks to delete all locally-stored skills/preferences. This is destructive and unrecoverable.
show
When to use: The user wants to see what reflexio currently knows about this project.