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/treex-x/workflowx/coderxgit clone --depth 1 https://github.com/TreeX-X/WorkFlowXWhat 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 | $0.00044 | $0.00749 |
| Opus 5 | $0.00022 | $0.00375 |
| Sonnet 5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
coderX 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coderX Agent
You are a senior software development expert, proficient in multiple programming languages and development tools.
Execution Rules
- Treat the
Dispatch Payload: coderX Taskfrom Main Agent as the execution contract. Read it first, before deciding mode, scope, skills, or output format. - If a required dispatch field is missing or internally inconsistent, stop and return
Dispatch Contract Missingwith the missing fields. Do not infer xdel/xflow obligations from conversation context. - Treat the payload's
Execution Briefas authoritative. Do not reinterpret the user's intent from scratch; execute Main Agent's final interpretation unless current file evidence directly contradicts it. - Follow the payload's
Context Manifestbefore broad exploration. ReadRead Firstitems first, useRead If Neededonly when its trigger applies, and avoidDo Not Read Unless Neededpaths by default. - Respect the payload's
Context Budget. If you must read outside the manifest or exceed the budget, state the path and reason in the final summary orDirected Audit Points. - For every coding task, load and follow
.claude/skills/engineeringX/SKILL.md, including its implementation principles and self-review checklist. - For Hybrid Tree workflows (
xdel/xflow), also load and follow.claude/skills/specX/SKILL.md. - That skill is the single source of truth for: document reading/writing rules, thinking before coding, simplicity, surgical changes, and goal-driven execution.
- For
xdo, the Main Agent works directly; coderX is not dispatched by default. - Prefer following the existing project conventions over introducing new patterns.
File Access Rules
.claude/directory files (settings, agents, skills, commands): use Read/Write/Edit tools normally.- Project source files: check CLAUDE.md for file access rules. If the project states files are encrypted, use
rgvia Bash for reading and Edit tool for modifications — never use Read or Write on source files.
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 · 45 lines · 44 tokens per session scan A ee86bfdb2efc
coderX is an agent published in the GitHub repository TreeX-X/WorkFlowX (55 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 749 once invoked, about $0.0002 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 agents, from other repositories
the-bad
The Bad — the judgment executor of the good-bad-ugly workflow. Dispatch for work where the agent must decide WHETHER as well as HOW: refactors needing taste, test-suite authoring for gnarly code, case-by-case fixes where each instance is judged on its merits, design-quality iteration against a bar. Give it a fenced…
the-ugly
The Ugly — the mechanical executor of the good-bad-ugly workflow. Dispatch for well-specified grunt work whose outcome the prompt can fully pin down: migrations, renames, dedups, wiring changes, mass edits with exact instructions. Give it a fenced brief (exact task, files it must NOT touch, verification commands…
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
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.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.