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/djrhails/dotfiles/session-searchnpx skills add DJRHails/dotfiles --skill session-searchgit clone --depth 1 https://github.com/DJRHails/dotfilesWhat 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 | $0.00038 | $0.00623 |
| Opus 5 | $0.00019 | $0.00311 |
| Sonnet 5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
session-search 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.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Search
Search across all Claude Code session transcripts (every ~/.claude*/ config dir — .claude, .claude-ant, etc. — plus ~/.agents/) and Pi agent sessions (~/.pi/agent/sessions/), including Pi artifacts (plans, context docs, etc.).
When to use
- User asks "which session did we talk about X?"
- User wants to find a previous conversation by topic
- User needs to recall advice, code, or decisions from past sessions
Usage
Run the helper script with a quoted search query:
python3 ~/.claude/skills/session-search/scripts/search.py "your search terms"
All terms must appear in the same text block for a match (AND logic).
Options
| Flag | Default | Purpose |
|---|---|---|
--project <str> |
all | Filter to project dirs containing this string |
--context <n> |
200 | Characters of context around each match |
--limit <n> |
10 | Max sessions to display |
Examples
# Find sessions discussing margin notes
python3 ~/.claude/skills/session-search/scripts/search.py "margin notes"
# Narrow to a specific project
python3 ~/.claude/skills/session-search/scripts/search.py "LoRA" --project kb
# More context, more results
python3 ~/.claude/skills/session-search/scripts/search.py "deploy" --context 400 --limit 20
Output
For each matching session the script prints:
- Session ID and resume command (
claude::resume <id>— cd's into the session's original directory and resumes via the owning config profile; defined inmodules/claude/aliases.zsh) - Date, project, and the original prompt
- Up to 3 matching snippets with role labels and line numbers
Notes
- Searches
~/.claude*/projects/(all config-dir variants),~/.agents/projects/, and~/.pi/agent/sessions/for session transcripts - History index from every
~/.claude*/history.jsonlplus~/.agents/history.jsonl - Pi sessions are identified with
[pi]label and resume viapi::resume <id>(cd's into the session's directory, thenpi --session <id>; defined inmodules/pi/aliases.zsh) - Pi artifacts (markdown files under
artifacts/) are also searched and labelled(pi artifact: <name>) - Searches text content from user and assistant messages (skips tool calls, binary data, etc.)
- Subagent files are not searched (only top-level session files)
What ships with it
1 file 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.
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.
- 2d ago First seen · 63 lines · 38 tokens per session scan A f5e7c5c8b8bf
session-search is a skill published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 623 once invoked, about $0.0002 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
autopilot-batch
Fan out a batch of autopilot-queued issues to parallel background worktree subagents — each runs /autopilot at the build model from its 'model:' label — with a gating review at Opus 5 or above and never below the build (Opus reviews Sonnet and Opus builds, Fable reviews Fable builds).
todoist-cli
Manage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the td CLI. Use when the user wants to view, create, update, complete, or organize Todoist items, or mentions tasks, inbox, today, upcoming, projects, labels, or filters.
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
qa-handoff
Generate a hands-on QA testing guide as a self-contained HTML page — for Rails apps or static (Hugo) sites. --publish uploads the HTML to the project's configured QA host.
walkthrough
Generate a hands-on browser walkthrough of a PR's user-facing changes to exercise before review; --publish posts the final version to the PR for QA.
dustoff
Assess a project that's been dormant for months and produce a prioritized re-entry plan — lifecycle stage, what's stale or broken, and how far the project's tooling has drifted from current conventions — delegating every fix to the skill that owns it, and optionally capturing the plan as a tracking issue that survives…