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/ahmedawan-oracle/claude-code-plugins/aidp-agent-flowsnpx skills add ahmedawan-oracle/claude-code-plugins --skill aidp-agent-flowsgit clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-agent-flows)<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-agent-flows"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-agent-flows.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00141 | $0.04779 |
| Opus 5 | $0.00071 | $0.02389 |
| Sonnet 5 | $0.00028 | $0.00956 |
| Haiku 4.5 | $0.00014 | $0.00478 |
Grade A, and why
aidp-agent-flows 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 4d 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.
aidp-agent-flows — agent flow lifecycle
Discover, author, deploy, and run agent flows through the AIDP REST AgentFlows API via
oci raw-request. No MCP and no ai-data-engineer-agent repo are required.
CLI gap (no invented commands): the official
aidpCLI v1.0.0 has no agent-flow group (the Python SDK shipsagent_flowmodels only). Agent-flow CRUD / deploy / run / sessions / guardrails all stay on the REST API (LA20240831, may be unprovisioned). Do not assume anaidp agent-flowcommand exists — see references/aidp-cli-map.md.
LA + verify-first (no-fabrication): AgentFlows is Limited Availability on
20240831(not in the GAaiwap/docs but still active). Path is workspace-scoped:…/dataLakes/<ocid>/workspaces/<ws>/agentFlowsreturned 200 live (2026-06-10,oaseceal); the lake-level…/dataLakes/<ocid>/agentFlows(no workspace) 404s — that earlier 404 was the wrong path, not necessarily missing provisioning. Still confirm the route with a live read before any write (provisioning can vary by tenancy), and record results inreferences/rest-endpoint-map.md. Frame the whole lifecycle as LA, not GA.
When to use
- "List/show agent flows" (read). "Create/update/deploy/run a flow", "manage flow sessions/guardrails", "attach compute to a flow" (write).
- "Connect my flow/agent to a remote MCP server / OAC MCP / ADW Select AI MCP / an MCP tool" → add an
MCP_TOOLnode (see the Native MCP Client Support section below).
Auth + base URL
Use the auth ladder and base URL in references/oci-raw-request.md:
https://aidp.<region>.oci.oraclecloud.com/20240831/dataLakes/<dataLakeOcid>/…, --profile DEFAULT
(api_key); on 401/403/"Security Token" refresh AIDP_SESSION and retry with --auth security_token.
Read / discover (REST — primary)
GET …/workspaces/<ws>/agentFlows— enumerate flows (workspace-scoped; live 200 onoaseceal2026-06-10).GET …/workspaces/<ws>/agentFlows/<key>— flow detail for authoring.- A 404 usually means you dropped the
…/workspaces/<ws>/segment (the lake-level…/agentFlowsdoesn't exist) — re-check the path first; if the workspace-scoped path also 404s, AgentFlows isn't provisioned in this tenancy (see note above) — surface that rather than assuming the flow is missing. - Optional accelerator: if an
aidpMCP happens to be configured,list_agent_flowsis a convenience read over the same control-plane. It is not required and not the primary path.
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.
- 4d ago First seen · 248 lines · 141 tokens per session scan A 718c18c5fa8d
aidp-agent-flows is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 4,779 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…