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/GabsFranke/claude-code-github-agentWrote 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/gabsfranke/claude-code-github-agent/retrospect)<a href="https://agentmods.dev/commands/gabsfranke/claude-code-github-agent/retrospect"><img src="https://agentmods.dev/badge/commands/gabsfranke/claude-code-github-agent/retrospect/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/commands/gabsfranke/claude-code-github-agent/retrospect"><img src="https://agentmods.dev/badge/commands/gabsfranke/claude-code-github-agent/retrospect.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 | $0.00013 | $0.02218 |
| Opus 5.5 | $0.00005 | $0.00887 |
| Sonnet 5.5 | $0.00003 | $0.00444 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
retrospect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospector
Analyse a completed agent session transcript, identify concrete problems with how
the agent performed, and improve the instruction files that govern that agent's
behaviour. Propose changes as a pull request to the develop branch.
Arguments: "$ARGUMENTS"
- First argument: path to the session transcript summary (markdown, pre-processed)
- Second argument: workflow name (e.g.
review-pr,fix-ci,triage-issue,generic) - Third argument: target repository the session worked on (owner/repo, for context)
- Fourth argument (optional): number of turns the session took
- Fifth argument (optional):
errorif the session errored, otherwise omitted - Sixth argument (optional):
subagentif this is a subagent session, otherwise omitted
Step 1 — Read the transcript summary
Read the transcript summary at the path given in the first argument.
The file is a structured markdown summary of the session, not the raw JSONL. It includes:
- Total turn count and error count
- List of subagents invoked (via Agent tool calls)
- Timeline of assistant messages, tool calls, and tool results
- Summary of all tool errors
Check the sixth argument to determine session type:
- If sixth argument is
subagent: This is a subagent execution session - Otherwise: This is a main workflow session
Agent Tool Landscape
When analyzing transcripts, you need to know what tools agents have access to so you can identify suboptimal tool usage. Agents in the sandbox have:
Search and exploration tools:
codegraph_search— Find symbols by name or patterncodegraph_context— 360-degree view of a symbol's role and relationshipscodegraph_callers/codegraph_callees— Trace how symbols are used across the codebase
File tools: Read, Grep, Glob, Write, Edit
GitHub tools: mcp__github__* (PRs, issues, comments, reviews)
Delegation tools: Agent (subagents), Skill (load knowledge)
Skills: codebase-context (search system guide), git-worktree-workflow
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.
- 26d ago Changed · -1 lines 5bd3f2a9f31b
- 1mo ago First seen · 242 lines · 13 tokens per session scan A ea5ada183cdd
retrospect is a command published in the GitHub repository GabsFranke/claude-code-github-agent (5 stars, last pushed 26d ago), licensed MIT. It adds 13 tokens to every session and 2,218 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.