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 commands/dimitrigeelen/agentic-engineering-framework/capturegit clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-frameworkWrote 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/commands/dimitrigeelen/agentic-engineering-framework/capture)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/capture"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/capture.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 | $0.00000 | $0.00599 |
| Opus 5 | $0.00000 | $0.00300 |
| Sonnet 5 | $0.00000 | $0.00120 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
capture 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 today.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/capture - Emergency Conversation Capture
When the user types /capture, execute this workflow to save the current
conversation to disk before it is lost.
Step 1: Check active task
Read .context/working/focus.yaml to get current_task.
If no active task or current_task is empty:
- Print: "No active task. Run
fw work-on 'topic'first to create one, then retry /capture." - Stop here.
Step 2: Extract conversation from transcript
Run:
python3 agents/capture/read-transcript.py
This reads the live JSONL transcript and returns JSON with:
turns: array of{role, content, timestamp}objectscaptured_turns: how many turns were capturedcapture_mode: how the boundary was detected
If the script exits non-zero or returns empty turns, print the warning from stderr and stop.
Step 3: Write the artifact
Generate the artifact path:
docs/reports/{current_task}-capture-{YYYY-MM-DD-HH}.md
Write the file with this structure:
# {current_task}: Conversation Capture — {YYYY-MM-DD HH:MM}
> Captured via /capture | Turns: {captured_turns} | Mode: {capture_mode}
> Task: {current_task}
## Topic / Problem Statement
{Summarise in 2-3 sentences what this conversation is about, based on the turns.}
## Key Insights
{List the most important findings or conclusions reached, as bullet points.
Extract from the conversation content — don't hallucinate.}
## Options Explored
{If alternatives were discussed, list them with brief notes on each.
Skip this section if no options were compared.}
## Decisions Made
{List any explicit decisions or directions agreed on.
Skip if no decisions were made.}
## Open Questions
{List anything that was raised but not resolved.}
## Conversation Log
{For each turn in the turns array, format as:}
**Human** _{timestamp}_
{content}
---
**Agent** _{timestamp}_
{content}
---
Step 4: Commit
Run:
fw git commit -m "{current_task}: /capture — conversation artifact"
Step 5: Report back
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.
- today First seen · 106 lines · 0 tokens per session scan A 7f8618999320
capture is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 599 tokens. 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 2026-09-04.
Other commands, from other repositories
list
List recent task executions across all agents.
pause
Pause one or more schedules to temporarily stop automated executions.
service-check
Request each agent to run a self-diagnostic to validate their runtime setup.
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
request-research
Ask the researcher to investigate a specific topic.
schedules
Quick overview of all schedules across the platform.