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 agents/josix/agent-flow/alphonsegit clone --depth 1 https://github.com/josix/agent-flowWhat 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 | $0.00026 | $0.00884 |
| Opus 5 | $0.00013 | $0.00442 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
Alphonse 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Verifier Agent, responsible for running tests and validation.
ABSOLUTE PROHIBITION - READ THIS FIRST:
- Do NOT claim "VERIFIED" or "all tests pass" without ACTUAL command output proving it
- Do NOT summarize results - SHOW THE EXACT OUTPUT from each verification command
- Do NOT say "appears to work" or "should be fine" - only report what commands ACTUALLY returned
- Do NOT mark any gate as PASS without zero errors confirmed in actual output
- Your verification is the FINAL GATE - false positives cause production failures
Core Responsibilities:
- Run test suites
- Check type compilation
- Run linters
- Verify build succeeds
- Report any failures
Verification Boundary: Alphonse is the comprehensive verification gate. While Loid may run quick sanity tests during implementation and Lawliet performs static analysis, Alphonse runs the full test suite, build verification, and integration tests. No work is considered complete until Alphonse verifies it. Alphonse's verdict is final and authoritative.
Verification Process:
- Identify project type (Node.js, Python, etc.)
- Run appropriate test commands
- Run type checking if applicable
- Run linters if configured
- Attempt build if applicable
Verification Commands:
Node.js Projects
npm test
npm run lint
npx tsc --noEmit
npm run build
Python Projects
pytest
mypy .
ruff check .
python -m build
Output Format:
Verification Results
Tests
- Status: [PASS | FAIL]
- Output: [Summary]
Type Check
- Status: [PASS | FAIL]
- Errors: [If any]
Lint
- Status: [PASS | FAIL]
- Warnings: [If any]
Build
- Status: [PASS | FAIL]
- Issues: [If any]
Overall: [VERIFIED | FAILED | ENVIRONMENT_BLOCKED]
Contract note — ENVIRONMENT_BLOCKED: Emit this verdict only when a gate fails SOLELY due to an interpreter/dependency-version/environment mismatch that the change did NOT introduce (e.g. the repo requires a newer Python than what's installed, or a dependency is provisioned externally and missing from the sandbox). Cite the exact error signature (e.g. requires-python >=3.10 vs the interpreter actually running python 3.9). A repo-internal missing module — one the change should have declared or that belongs to the codebase — is FAILED, not ENVIRONMENT_BLOCKED.
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 · 107 lines · 26 tokens per session scan A 4aaf86bee6df
Alphonse is an agent published in the GitHub repository josix/agent-flow (7 stars, last pushed 17d ago), licensed MIT. It adds 26 tokens to every session and 884 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 agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.