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-read-conversationnpx skills add itdove/devaiflow --skill daf-read-conversationgit 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-read-conversation)<a href="https://agentmods.dev/skills/itdove/devaiflow/daf-read-conversation"><img src="https://agentmods.dev/badge/skills/itdove/devaiflow/daf-read-conversation.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 | $0.00017 | $0.00417 |
| Opus 5 | $0.00009 | $0.00209 |
| Sonnet 5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
daf-read-conversation 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.
What it actually says
Read the conversation history from another repository in this multi-project session to understand work done in related codebases.
USAGE:
- First, run
/daf list-conversationsto see all available conversations - Then use this command to read a specific conversation's history
IMPORTANT: You can only read conversations from OTHER repositories, NOT the current one. Reading the current conversation would duplicate the context you already have.
To read a conversation:
# Get session info to find conversation details
daf info
# The output shows all conversations with their:
# - Working directory name (e.g., "backend-api", "frontend-ui")
# - Repository name
# - Claude Code session UUID
# - Git branch
# Read the conversation file directly using the Claude Code session UUID:
# Conversation files are stored at: ~/.claude/projects/<encoded-path>/<uuid>.jsonl
# Example workflow:
# 1. Get the session UUID for the conversation you want to read
# 2. Find the encoded path for that repository
# 3. Read the .jsonl file
# Note: The .jsonl file contains the full conversation history in JSON Lines format
# Each line is a JSON object representing one message in the conversation
MULTI-CHOICE SELECTION: If there are multiple conversations in this session, you can provide a multi-choice interface:
- List all conversations EXCEPT the current one
- User selects which conversation to read
- You read that conversation's .jsonl file
WHAT TO LOOK FOR: When reading another conversation, focus on:
- What features were implemented
- API contracts or interfaces defined
- Data models or schemas created
- Configuration changes made
- Dependencies or integration points
- Decisions about implementation approach
This helps maintain consistency across the multi-repository feature implementation.
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 · 57 lines · 17 tokens per session scan A d601eb08b9cb
daf-read-conversation is a skill published in the GitHub repository itdove/devaiflow (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 417 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…
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…
meridian-etl
Debug and work with Meridian's ETL pipeline. Covers session boundary detection, cursor management, DB queries, and common failure modes.
meridian-mcp
Build, configure, and debug the Meridian MCP server. Exposes app session data to AI tools via the Model Context Protocol.
github-image-upload
Upload local images and other files (PDF, zip, log, …) to GitHub and embed them in a pull request description, an issue, or a comment — producing canonical github.com/user-attachments URLs (private-repo uploads stay private). Use when asked to "attach a screenshot to the PR", "add an image to the PR description", "put…
Jira QA Workflows
Run QA work in Jira like a professional, bug lifecycle and triage, JQL queries for testers, quality dashboards, sprint QA rituals, and REST API automation for bulk bug operations and reporting.