session-backfill

A session-history tool that turns Claude Code conversation transcripts into structured notes for each project. It extracts the goal, result, decisions, blockers, next steps, and references instead of keeping only raw transcript files.

In plain words
What is it for?
It helps backfill missing session notes from Claude Code’s JSONL transcript files and organize them in a project-based notes folder.
Why use it?
It makes past coding work searchable and useful when automatic session notes were left as empty placeholders. Rerunning it does not duplicate summaries that already exist.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/hamchowderr/braynee/session-backfill
Any agent
npx skills add hamchowderr/braynee --skill session-backfill
Clone the repo
git clone --depth 1 https://github.com/hamchowderr/braynee

Made for: Claude Code, Codex.

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00096 $0.01324
Opus 5 $0.00048 $0.00662
Sonnet 5 $0.00019 $0.00265
Haiku 4.5 $0.00010 $0.00132

Measured 2d ago against content hash 48385c75be89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-backfill 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/backfill.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/session-backfill/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Backfill Skill

Turn empty braynee session-auto-track stubs into substantive per-project session notes by distilling the real Claude Code conversation history.

Why

Braynee's session-auto-track creates a one-line stub session note when each CC session starts. The stubs never get filled in — they say "Waiting for user to state goal" and "(none yet)" forever. Meanwhile the actual conversation lives in ~/.claude/projects/<encoded-path>/*.jsonl. QMD indexes only the stubs, so project history is unsearchable.

This skill reads each .jsonl, filters the tool-call noise, distills the conversation skeleton, and writes a structured summary into <vault>/2. Areas/Sessions/<Project>/<date>-<slug>-<type>-<id>.md.

Idempotent: if a structured note already exists for a session_id, it's skipped. Safe to rerun.

Distillation: no API billing by default

The default backend is claude -p — it uses your local Claude Code subscription via OAuth. No ANTHROPIC_API_KEY, no Console credits, no infisical, no per-session cost. The script explicitly strips ANTHROPIC_API_KEY from the claude -p subprocess env so it can never silently fall back to API billing.

--use-api is an explicit opt-in for the raw Anthropic API (Console credits). Use it only if you specifically want API billing and have set ANTHROPIC_API_KEY yourself. It is never required and never the default.

Commands

# Single project (pilot use) — uses `claude -p`, no API billing
python3 {baseDir}/scripts/backfill.py --project sophon-webapp

# Dry run — print what would be created, no distillation at all
python3 {baseDir}/scripts/backfill.py --project sophon-webapp --dry-run

# Limit to N most-recent sessions per project
python3 {baseDir}/scripts/backfill.py --project sophon-webapp --limit 5

# All projects (the big backfill)
python3 {baseDir}/scripts/backfill.py --all

# Point at a non-default vault location
python3 {baseDir}/scripts/backfill.py --all --vault "/path/to/Obsidian Vault"

# Opt in to the raw API (Console billing — only if you explicitly want it)
ANTHROPIC_API_KEY=... python3 {baseDir}/scripts/backfill.py --project sophon-webapp --use-api

Read the full file on GitHub · 121 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 121 lines · 96 tokens per session scan A 48385c75be89

Subscribe to this mod's changes

session-backfill is a skill published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 96 tokens to every session and 1,324 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens