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.
git clone --depth 1 https://github.com/bacchus-labs/wranglerWrote 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/commands/bacchus-labs/wrangler/analyze-session-gaps)<a href="https://agentmods.dev/commands/bacchus-labs/wrangler/analyze-session-gaps"><img src="https://agentmods.dev/badge/commands/bacchus-labs/wrangler/analyze-session-gaps.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 | $0.00010 | $0.05694 |
| Opus 5 | $0.00005 | $0.02847 |
| Sonnet 5 | $0.00002 | $0.01139 |
| Haiku 4.5 | $0.00001 | $0.00569 |
Grade A, and why
analyze-session-gaps 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 — 731 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are analyzing the current session to identify workflow gaps, skill deficiencies, or process regressions that caused user frustration.
Input
User provided description: "{user's description of the problem}"
Your Task
Phase 1: Session Analysis
-
Understand the Problem
- Parse user's description carefully
- Identify what went wrong from the user's perspective
- Determine the gap between user expectation and reality
- Consider the context of their frustration
-
Trace Conversation History
- Review recent messages in this session (last 20-30 messages)
- Identify the specific point where the workflow failed
- Note which skills were invoked (if any)
- Note which commands were executed
- Detect what SHOULD have happened but didn't
- Look for patterns of similar failures in the conversation
-
Classify the Gap
Determine the gap type from these categories:
-
MISSING_SKILL: No skill exists for this scenario
- Example: "No skill to check code style consistency across files"
- Indicator: "I wish there was a way to..." or "Nothing caught this problem"
-
BROKEN_SKILL: Skill exists but didn't work correctly
- Example: "The verification skill ran but missed the bug"
- Indicator: Skill was invoked but failed to prevent the issue
-
SKILL_NOT_INVOKED: Skill exists but wasn't used when it should have been
- Example: "Constitutional check skill exists but wasn't triggered"
- Indicator: "We have a skill for that, why didn't you use it?"
-
WORKFLOW_GAP: Skills exist but aren't properly connected
- Example: "Skills for testing and deployment exist but no bridge between them"
- Indicator: Multiple steps needed but no orchestration
-
VERIFICATION_GAP: No check exists to prevent the issue
- Example: "Nothing verified tests were actually run before claiming success"
- Indicator: Agent made claims without evidence
-
PROMPT_GAP: Skill exists but prompts are unclear or ignored
- Example: "Skill says to do X, but agent did Y instead"
- Indicator: Skill instructions ambiguous or contradictory
-
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 · 731 lines · 10 tokens per session scan A 64a293ae12a2
analyze-session-gaps is a command published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 5,694 once invoked, about $0.0001 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 commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.