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 ethanolivertroy/my-agent-stuff --skill conversation-dumpgit clone --depth 1 https://github.com/ethanolivertroy/my-agent-stuffWrote 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/ethanolivertroy/my-agent-stuff/conversation-dump)<a href="https://agentmods.dev/skills/ethanolivertroy/my-agent-stuff/conversation-dump"><img src="https://agentmods.dev/badge/skills/ethanolivertroy/my-agent-stuff/conversation-dump.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 5.1 | $0.00111 | $0.00880 |
| Opus 5 | $0.00056 | $0.00440 |
| Sonnet 5 | $0.00022 | $0.00176 |
| Haiku 4.5 | $0.00011 | $0.00088 |
Grade A, and why
conversation-dump 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 7d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversation Dump - Full Markdown Transcript
Create a faithful Markdown record of the current Pi conversation. This is for full-fidelity capture, not an end-of-session summary.
Use When
Use this skill when the user asks to:
- dump this conversation
- save this conversation to Markdown
- export this chat
- log this session to a file
- save the chat log
- output the full transcript
Do not trigger on Mischief Managed territory, such as "wrap up this session," "save a session summary," or "write this to Pi-Sessions." Mischief Managed writes a compact summary. Conversation Dump writes the full readable transcript.
Output Goal
The Markdown file should preserve:
- user requests as close to verbatim as possible
- assistant responses in full when available in context
- tool calls and commands that materially changed state
- key command output, summarized only when output is huge
- file paths touched
- decisions made
- follow-up items
Do not reduce the session to a short summary. Prefer a structured transcript with enough context that future-you can reconstruct what happened.
Destination
Use this priority order:
- explicit path or folder requested by the user
- current working directory if the user says "here" or implies the repo/project
- ask one clarifying question if destination is unclear
Good default filename:
conversation-dump-{YYYY-MM-DD-HHMM}-{short-slug}.md
If the user wants it in Obsidian, use the user-provided vault path. Do not assume the Pi session summary folder unless they explicitly ask for it.
Workflow
1. Gather metadata
Run one shell command:
date +%Y-%m-%d-%H%M; date +"%b %d, %Y"; pwd; git rev-parse --abbrev-ref HEAD 2>/dev/null || echo ""; basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo ""; git remote get-url origin 2>/dev/null || echo ""
Map to:
DATETIMEPRETTY_DATEDIRBRANCHREPOREPO_URL
2. Build the dump
Use this structure:
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.
- 7d ago First seen · 135 lines · 111 tokens per session scan A e1882962bf9e
conversation-dump is a skill published in the GitHub repository ethanolivertroy/my-agent-stuff (11 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 880 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
siyuan
Query and edit a SiYuan knowledge base via its API.
xlsx
Create, read, edit Excel .xlsx workbooks and CSVs.
pptx-author
Build PowerPoint decks headless with python-pptx.
box
Box manages cloud files, sharing, search, and metadata.