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 skills add itdove/devaiflow --skill daf-workflowgit clone --depth 1 https://github.com/itdove/devaiflowWrote 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/itdove/devaiflow/daf-workflow)<a href="https://agentmods.dev/skills/itdove/devaiflow/daf-workflow"><img src="https://agentmods.dev/badge/skills/itdove/devaiflow/daf-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/itdove/devaiflow/daf-workflow"><img src="https://agentmods.dev/badge/skills/itdove/devaiflow/daf-workflow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.03283 |
| Opus 5.5 | $0.00027 | $0.01313 |
| Sonnet 5.5 | $0.00014 | $0.00657 |
| Haiku 4.5 | $0.00007 | $0.00328 |
Grade A, and why
daf-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevAIFlow Session Context
This skill is used by every supported AI agent or IDE integration. In this document, agent session means the configured backend for the current session (for example Claude Code, Codex, GitHub Copilot, Cursor, Windsurf, Aider, Continue, OpenCode, Crush, or an Ollama-backed adapter). Use an agent-specific name or path only when the instruction explicitly calls for backend-specific behavior.
Session identifiers are also backend-specific. Use the active conversation's
agent session ID from daf active or daf info; do not substitute the most
recently opened session from another agent or repository.
Run this command to check the session environment:
echo "DAF_SESSION_NAME=$DAF_SESSION_NAME" "DAF_COMMAND=$DAF_COMMAND"
Important: Use this command exactly as written — the text must match the agent's permission pattern. Do not rephrase or restructure.
If DAF_SESSION_NAME is set (non-empty), this is a managed DevAIFlow session — follow the initialization steps below. If empty, skip to the Standalone Workflow Guide section at the bottom.
Session Initialization
When DAF_SESSION_NAME is set, perform these steps before doing any other work:
1. Read Session Metadata
daf info $DAF_SESSION_NAME
This shows: session name, goal, issue key, status, working directory, branch, workspace, session type, and conversation history.
DAF-managed conversation titles
The DAF session name (Name in daf info) identifies the session; the
goal (--goal) describes the work; the backend's LLM conversation title
is separate display metadata.
For Claude Code, Pi, and OpenCode, DAF manages native title setting at launch
and on supported resume paths. The title is the exact current DAF session
name from metadata, not the goal, issue summary, or an agent-generated task
summary. This applies to daf new, daf open, daf git new, daf jira new,
and daf investigate; read-only and ticket-creation constraints still apply.
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 Changed · +18 lines 821142bc9678
- 10d ago Changed · +3 lines 6fc5ad205dd5
- 1mo ago Changed · +18 lines 6386572e577c
- 1mo ago Changed · +19 lines f7bd87015e69
- 1mo ago First seen · 282 lines · 68 tokens per session scan A dcafedda4695
daf-workflow is a skill published in the GitHub repository itdove/devaiflow (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 68 tokens to every session and 3,283 once invoked, about $0.0003 per session on Opus 5.5. 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
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
metagit-projects
Ongoing workspace and project management for OpenClaw and Hermes agents. Use when starting work, organizing repos, or before creating a new project folder so existing metagit projects are reused instead of duplicated.
metagit-control-center
Use when running metagit as an MCP control center for multi-repo awareness, guarded sync, and operational knowledge across ongoing agent tasks.
metagit-rewrite-campaign
Orchestrate a reference-implementation rewrite across source and target repos using campaigns, parity registry conventions, objectives, and subagent handoffs.
metagit-sharing-state
Configure shared coordination state (objectives, handoffs, approvals, events) across multiple agents and machines via METAGITSTATEURL, optional DynamoDB / MongoDB DocumentStore backends, and the ops HTTP path. Use when Hermes subagents, CI runners, or humans must see the same objective queue without Syncthing JSON…
workingon
Record the work done in this Claude Code session in the configured ticketing tool (Jira, Linear, GitHub Issues, Trello or Vikunja), creating the ticket, adding a short progress comment, linking an existing one or closing it. Use it when the [workingon] hook reports unrecorded work, when the user types /workingon, and…