Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add oborchers/fractional-cto/plugin install retellWrote 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/oborchers/fractional-cto/conversation-format)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/conversation-format"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/conversation-format/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/oborchers/fractional-cto/conversation-format"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/conversation-format.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 | $0.00087 | $0.02161 |
| Opus 5.5 | $0.00035 | $0.00864 |
| Sonnet 5.5 | $0.00017 | $0.00432 |
| Haiku 4.5 | $0.00009 | $0.00216 |
Grade A, and why
conversation-format 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 5d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversation Format
Overview
Claude Code stores conversation transcripts as JSONL files in ~/.claude/projects/<encoded-path>/<uuid>.jsonl. Each line is a JSON object with a type field that determines its shape and narrative value. A typical 15 MB conversation contains only ~338 KB of signal (~2.2%). The parser's job is to extract that signal deterministically, at zero token cost.
File Locations
Main conversations:
~/.claude/projects/<encoded-path>/<conversation-uuid>.jsonl
Path encoding replaces / with - in the project's absolute path:
/Users/oliver/Desktop/Vault.nosync/vaultencodes to-Users-oliver-Desktop-Vault-nosync-vault
Subagent transcripts (same JSONL format):
<conversation-uuid>/subagents/agent-<agent-id>.jsonl
Compact summaries — system-generated conversation recaps from /compact. Filename pattern: agent-acompact-*.jsonl. These are NOT real subagent research. Skip them as subagent content, but they can serve as chapter bridges (they are high-quality "previously on..." summaries).
Entry Types
Signal entries (extract)
| Type | Key fields | Narrative value |
|---|---|---|
user |
message.content (string or content blocks) |
Human requests, reactions, pivots — drives the story |
assistant |
message.content (array of content blocks) |
Responses, decisions, deliverables — the action |
system with subtype: turn_duration |
durationMs (milliseconds) |
Pacing metadata ("after 3 minutes of research..."). Typical range: 5,000-300,000 ms. |
Noise entries (drop entirely)
| Type | Why skip |
|---|---|
progress |
Hook events, intermediate states — no narrative value |
file-history-snapshot |
Undo/restore snapshots — internal bookkeeping |
queue-operation |
Internal scheduling — never user-visible |
system (other subtypes) |
Metadata with no narrative content |
Content Block Types
Assistant content blocks
Assistant messages contain an array of content blocks. Extract in this priority:
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.
- 5d ago First seen · 194 lines · 87 tokens per session scan A 0744c15c58ec
conversation-format is a skill published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 2,161 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 2026-10-13.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.