coding-agent-sessions

MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, Senpi/pi, oh-my-pi (omp), gajae-code (gjc), OpenClaw, Factory Droid, Amp, Gemini/Kimi/Qwen CLIs, Codebuff, Roo/Kilo/Cline, Kodu, Cursor CLI, Aider, Aside browser-agent sessions, or unknown local agent logs. Covers transcripts, session IDs, rollout JSONL, state SQLite, Claude projects/pre-compact histories, OpenCode messages/parts, child/subagent linkage, cwd/model/time/token filters, archives, and cost clues. Expands fuzzy recall into parallel query lanes and first probes known stores so absent platforms are skipped cheaply. Triggers: coding agent sessions, Codex/Claude/OpenCode/Senpi/pi/oh-my-pi/omp/gajae-code/gjc/OpenClaw/Droid/Amp/Kodu/Cursor/Aider/Aside sessions, transcript search, session history, session ID, read transcript, token usage, subagent sessions, what did I do yesterday, did we already do this.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable body with a clear phased workflow, real executable commands, and clean progressive disclosure to verified bundle references. Minor conciseness losses from command repetition and a few niche asides, and the verification checkpoint could be tighter.

Suggestions

Remove the duplicate list/find/read command block in 'Codex Notes' since the same invocations already appear in PHASE 0; keep only the Codex-specific pointer to references/codex.md.

Tighten the verification step (PHASE 0 step 5) into an explicit checkpoint: e.g., 'Before summarizing, open the raw path from the chosen result and confirm the cited prompt/event exists; if not, fall back to explorer lanes.'

Consider moving the niche exclusions (Aside hardlink mirror, Copilot OTEL/Mux/Antigravity usage-only sources) into references/all-platforms.md to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic concept explanations), but the Codex Notes section re-shows list/find/read commands already demonstrated in PHASE 0, and a few niche asides (Aside hardlink mirror, excluded usage-only sources) could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout ('python3 scripts/find-agent-sessions.py find "commit" --from 7d --platform senpi --platform opencode') with concrete flag combinations covering the common cases.	5 / 5
Workflow Clarity	PHASE 0 is a clear numbered sequence (1-5) including an explicit verification step ('Verify by opening raw transcripts for claims') and a Troubleshooting table for recovery, but the verify step is softer than a hard validate-fix-retry checkpoint and the explorer-lane fallback is suggested rather than prescribed.	4 / 5
Progressive Disclosure	Well-signaled one-level-deep references: the platform router table maps each product to a real file (references/codex.md, claude.md, senpi.md, opencode.md, all-platforms.md, all confirmed present), keeping the SKILL.md an overview while details live in bundle files.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exceptionally complete description: explicit 'MUST USE when' trigger guidance, concrete actions and artifacts, comprehensive natural trigger terms with synonyms, and a distinct niche. The only mild concern is density/length from platform enumeration, but every enumerated item is a genuine trigger, not padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('find, read, list, search, inspect, fetch, export, or reconstruct') plus concrete artifacts ('rollout JSONL, state SQLite, Claude projects/pre-compact histories, OpenCode messages/parts'), giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (find/read coding-agent sessions across products, covers transcripts/IDs/rollout/SQLite/child linkage/filters) and 'when' ('MUST USE when asked to...' plus a dedicated 'Triggers:' clause with concrete phrases).	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases including synonyms and aliases ('transcript search', 'session history', 'session ID', 'what did I do yesterday', 'did we already do this') alongside product aliases (omp, gjc), matching the anchor for full coverage including variations.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (local coding-agent session recovery across named products) with product-specific triggers, making it unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/coding-agent-sessions/SKILL.md
Commit: 10f9558

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.