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/nafjan/summon/byteplus-codergit clone --depth 1 https://github.com/Nafjan/summonWhat 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 | $0.00810 |
| Opus 5 | $0.00000 | $0.00405 |
| Sonnet 5 | $0.00000 | $0.00162 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
byteplus-coder 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BytePlus ModelArk Coding Plan coder (openai-compat)
Subscription-quota coding agent via ModelArk Coding Plan (/api/coding/v3).
Set BYTEPLUS_CODING_API_KEY. Text-only; pin a plan model id (not auto).
For always-PAYG Platform API use, skip this agent and pass an inline
openai-compat base_url ending in /api/v3 instead.
Uses your BytePlus ModelArk Coding Plan subscription via the OpenAI-compatible
endpoint. Bills against your Coding Plan subscription quota (not per-token
API credits). Set BYTEPLUS_CODING_API_KEY in your environment.
Pin a current Coding Plan model by task: deepseek-v4-flash for fast terminal loops,
deepseek-v4-pro for hard coding, glm-5.2 for long-horizon/large-repo work,
or dola-seed-2.0-code for agentic coding. The separate Ark marketplace currently
lists exact GA IDs deepseek-v4-flash-ga-260731, deepseek-v4-pro-ga-260813, and
glm-5-2-260617; those are cataloged for explicit arkcli +chat routes, but are not
silently substituted into this Coding Plan agent until plan eligibility and a minimal
text smoke are verified. kimi-k2.5 is a useful code/UI
alternative; the Seed Pro/Lite variants are general-purpose choices.
Strongly avoid legacy or superseded roster entries for new work: glm-5.1,
bytedance-seed-code, and gpt-oss-120b. The latter two were still listed but
failed live Coding Plan probes as of 2026-08-07. Roster presence is not proof of
availability: refresh with
arkcli plans model-list --plan coding-plan --format json, then validate a
minimal text call. (auto is an arkcli router and is refused by Summon's
raw API backend.)
All Coding Plan models are text-only — do not use this agent for tasks
requiring image/vision input (Cursor screenshots, diagrams, etc.). This
definition declares capability: text-only so Summon may dispatch it without
--allow-text-only on a single call; every such run still carries a loud
TEXT SEAT warning. Council/manifest still require SUMMON_ALLOW_TEXT_ONLY=1
(capability alone does not authorize fan-out). For repo/tool loops, use a
toolful CLI agent instead.
For other regions, override byteplus-coding in providers.json with your
regional base URL (e.g. ark.cn-beijing.volces.com/api/coding/v3).
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 · 64 lines · 0 tokens per session scan A 142c42ae98be
byteplus-coder is an agent published in the GitHub repository Nafjan/summon (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 810 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 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.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
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.