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/itdove/devaiflow/daf-confignpx skills add itdove/devaiflow --skill daf-configgit clone --depth 1 https://github.com/itdove/devaiflowWhat 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 | $0.00010 | $0.00527 |
| Opus 5 | $0.00005 | $0.00264 |
| Sonnet 5 | $0.00002 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
daf-config 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.
What it actually says
Display the current daf configuration including JIRA settings, workspace paths, and prompt defaults.
daf config show
What it shows:
JIRA Configuration:
- Project key
- Workstream
- Custom field mappings (epic link, workstream, acceptance criteria)
- Comment visibility settings
- Transition rules (on start, on complete)
Paths & Directories:
- Workspace directory
- Repository paths
- PR template URL
Prompt Configuration:
- Whether prompts are enabled/disabled for various operations
- Memory management settings
- Git auto-operations
Example output:
DevAIFlow Configuration
JIRA Settings:
Project: PROJ
Workstream: WORK
Epic Link Field: customfield_10014
Workstream Field: customfield_10015
Acceptance Criteria Field: customfield_10016
Transition on Start: In Progress
Transition on Complete: Code Review
Repositories:
Workspace: ~/development/workspace
Paths:
- backend-api: ~/development/workspace/backend-api
- frontend-app: ~/development/workspace/frontend-app
PR Template:
URL: https://github.com/YOUR-ORG/.github/blob/main/.github/PULL_REQUEST_TEMPLATE.md
Prompt Configuration:
Prompts Enabled: Yes
Memory Per Session: Default (system managed)
Use this to:
- Verify JIRA integration is configured correctly
- Check workspace and repository paths
- See custom field mappings
- Understand transition rules
- Debug configuration issues
View specific configuration subsets:
daf config show --prompts # Show only prompt configuration
daf config show --fields # Show available JIRA custom fields
daf config show --sync-filters # Show sync filter configuration
daf config context list # List available context files
daf config context show # Show context file contents
Related commands:
/daf help # Quick reference of all daf commands
daf config --help # Full list of config subcommands
Important:
- This is a READ-ONLY command - safe to run inside Claude Code
- To modify config, exit Claude Code and use
daf config set-*commands - Configuration is stored in $DEVAIFLOW_HOME/config.yaml
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 · 86 lines · 10 tokens per session scan A 0ca22adb8a58
daf-config is a skill published in the GitHub repository itdove/devaiflow (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 10 tokens to every session and 527 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 2026-08-31.
Other skills, from other repositories
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…
start-session
Session-bootstrap orchestration skill — its one job is to bring a working session online: apply senior-collaborator operating parameters, load prior feedback, pull the project's Jira backlog, and activate the standing plan-gate (analysis + plan + approval before any code edit). Trigger on /start-session or "start…
handover
Prepare a handover for continuing work in a new session. Use when the user asks to "hand over", "prepare handover", "wrap up for a new session", or "context dump".
standup
Compose and deliver today's standup from what you actually did — Jira, GitHub, Claude sessions, Calendar — via the enabled sink cards. Verbs — (default) full run; "dry-run" composes to the file sink only; "post" approves a held review-draft. Used by the scheduled headless runner and interactively ("post my standup"…
recap
Search and summarize your own work history from the standup archive — "what did I do between two dates", a TLDR of the week/month/quarter/half (appraisal season fuel), or a keyword search across everything you've shipped. Use for "recap my month", "what did I do in March", "find when I worked on X"…
extract-api
This skill should be used when the user asks to "extract API from", "import API from", "add commands from this repo", "register API from docs", "convert docs to CLI commands", "import Postman collection", or provides a GitHub repository URL, a documentation site URL, a Postman collection file/URL, or a local API…