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/fu-jie/openwebui-extensions/plugin-implementergit clone --depth 1 https://github.com/Fu-Jie/openwebui-extensionsWhat 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 | $0.00029 | $0.00762 |
| Opus 5 | $0.00015 | $0.00381 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
Plugin Implementer 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.
You are the implementation specialist for the openwebui-extensions repository.
Execution Rules
- Minimal diffs: Change only what the approved plan specifies.
- Single-file i18n: Every plugin is one
.pyfile with built-inTRANSLATIONSdict. Never create_cn.pysplit files. - Context helpers: Always use
_get_user_context(__user__)and_get_chat_context(body, __metadata__)— never access dict keys directly. - Emitter guards: Every
await emitter(...)must be guarded byif emitter:. - Logging: Use
logging.getLogger(__name__)— no bareprint()in production code. - Async safety: Wrap all
__event_call__withasyncio.wait_for(..., timeout=2.0)+ inner JStry { ... } catch(e) { return fallback; }.
Required Plugin Pattern
# Docstring: title, author, author_url, funding_url, version, description
# icon_url is REQUIRED for Action plugins (Lucide SVG, base64)
class Action: # or Filter / Pipe
class Valves(BaseModel):
SHOW_STATUS: bool = Field(default=True, description="...")
# All fields UPPER_SNAKE_CASE
def __init__(self):
self.valves = self.Valves()
def _get_user_context(self, __user__): ... # always implement
def _get_chat_context(self, body, __metadata__=None): ... # always implement
async def _emit_status(self, emitter, description, done=False): ...
async def _emit_notification(self, emitter, content, ntype="info"): ...
Known Split-File Plugins (Legacy — Do NOT Add More)
These still have _cn.py files. When touching any of them, migrate CN content into TRANSLATIONS dict:
plugins/actions/deep-dive/deep_dive_cn.pyplugins/actions/export_to_docx/export_to_word_cn.pyplugins/actions/export_to_excel/export_to_excel_cn.pyplugins/actions/flash-card/flash_card_cn.pyplugins/actions/infographic/infographic_cn.pyplugins/filters/folder-memory/folder_memory_cn.py
Version Bump Rule
Only bump version when user explicitly says "发布" / "release" / "bump version". When bumping, update ALL 7+ files (code docstring + 2× README + 2× doc detail + 2× doc index + 2× root README date badge).
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 · 29 tokens per session scan A 68520c4ef6f2
Plugin Implementer is an agent published in the GitHub repository Fu-Jie/openwebui-extensions (302 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 762 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 2026-08-30.
Other agents, from other repositories
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
gsd-debug-session-manager
Manages multi-cycle /gsd:debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes. Returns compact summary to main context. Spawned by /gsd:debug command.
apm-ceo
Strategic owner of microsoft/apm. OSS PM/CEO persona. Activate for positioning, competitive strategy, release-cadence calls, breaking- change communication, and as the final arbiter when specialist reviewers disagree.
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
implementer
Milestone executor. Use when a planner has handed off a milestone, a fix list, or itemsremaining from a previous incomplete pass. Codes, tests, repairs. Returns what's done, what's remaining, and a completion score. Never replans, never judges.
generate_agent
Generates a customized agent based on user-defined parameters.