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/urrhb/agentflow/sdlc-workernpx skills add UrRhb/agentflow --skill sdlc-workergit clone --depth 1 https://github.com/UrRhb/agentflowWhat 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 | $0.00065 | $0.02495 |
| Opus 5 | $0.00032 | $0.01247 |
| Sonnet 5 | $0.00013 | $0.00499 |
| Haiku 4.5 | $0.00006 | $0.00249 |
Grade A, and why
sdlc-worker 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc-worker
Execute AgentFlow pipeline work for the assigned worker slot.
Mode Detection
Detect whether running in plugin mode or standalone mode at startup:
- Check if
SendMessagetool is available in the current environment - Check if this worker was spawned by an orchestrator via
TeamCreate
| Condition | Mode | Behavior |
|---|---|---|
SendMessage available + spawned by orchestrator |
Plugin | Use message-based handoffs and progress reporting |
| Tools not available | Standalone | Fall back to comment-based updates and terminal polling (original behavior) |
Set MODE = "plugin" or MODE = "standalone" and log it at startup.
Handoff Protocol (Plugin Mode)
When MODE = "plugin", use SendMessage for all stage transitions and status updates instead of relying solely on PM tool comments.
Message Types
| Event | SendMessage Target | Body Format |
|---|---|---|
| Stage started | sdlc-orchestrate |
[<STAGE>:STARTED] Task <TASK_CODE>. Slot: T<N>. |
| Heartbeat | sdlc-orchestrate |
[HEARTBEAT] Task <TASK_CODE>. Slot: T<N>. Elapsed: <MIN>m. |
| Stage complete (pass) | sdlc-orchestrate |
[<STAGE>:<RESULT>] Task <TASK_CODE> complete. PR: <URL>. Cost: ~$<COST>. |
| Stage failed/rejected | sdlc-orchestrate |
[<STAGE>:<RESULT>] Task <TASK_CODE> failed. Reason: <SUMMARY>. |
| Blocked | sdlc-orchestrate |
[BUILD:BLOCKED] Task <TASK_CODE>. Reason: <REASON>. |
| Security warning | sdlc-orchestrate |
[SECURITY:WARNING] Task <TASK_CODE>. Suspicious content detected. |
Dual-Write Rule
In plugin mode, ALWAYS write updates to BOTH:
SendMessageto the orchestrator (primary, low-latency)- PM tool comment tags (secondary, persistence and auditability)
This ensures the PM tool remains the source of truth even if message delivery fails.
Progress Reporting (Plugin Mode)
When MODE = "plugin", send progress updates every 30 seconds during active work:
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 · 248 lines · 65 tokens per session scan A cfdf99a06313
sdlc-worker is a skill published in the GitHub repository UrRhb/agentflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 2,495 once invoked, about $0.0003 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 skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…