session-retro

A report on how a coding session used its token budget, based on the session transcript. Tokens are the small pieces of text used to measure model input and output.

In plain words
What is it for?
Use it at the end of a session to review large reads, verbose commands, repeated calls, and other sources of unnecessary usage.
Why use it?
It shows which tool results and repeated actions consumed the most context and whether that cost was justified. It also suggests cheaper ways to work next time.

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/justinthomas2/agentrc/session-retro
Any agent
npx skills add JustinThomas2/agentrc --skill session-retro
Clone the repo
git clone --depth 1 https://github.com/JustinThomas2/agentrc

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 590 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 $0.00047 $0.00590
Opus 5 $0.00023 $0.00295
Sonnet 5 $0.00009 $0.00118
Haiku 4.5 $0.00005 $0.00059

Measured 2d ago against content hash 8c36f2f1ca13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-retro 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 (analyze.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-retro/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TRANSCRIPT = $ARGUMENTS - if that reads as a literal placeholder instead of a file path, treat it as empty: the analyzer will find the current project's most recent transcript on its own.

The retro must cost a small fraction of the session it analyzes. All number-crunching happens in the bundled script; NEVER read the raw transcript into context - not even excerpts. Work only from the script's printed summary plus what you already remember of this session. Read-only throughout: analyze and report, change nothing.

Your task

  1. Run the analyzer bundled in this skill's directory: python3 <skill-dir>/analyze.py [TRANSCRIPT] It picks the newest transcript for the current project under ~/.claude/projects/ unless a path is given. If it errors (e.g. running under a harness that stores transcripts elsewhere), say so and ask me for the transcript path instead of guessing.
  2. Interpret the summary. The interesting signals:
    • the largest tool results, and whether each was necessary at that size (whole-file Read where a range or search would have done? verbose command output that could have been filtered?)
    • repeated calls to the same target - re-reads and retry loops
    • cache behavior: read is re-served context and cheap; created plus fresh input is what actually grew the bill, and final context is how full the window got
    • anything you remember doing the long way (trial-and-error loops, work that a subagent or a narrower query could have done cheaper)
  3. Report, briefly - the whole retro should be a screenful:
    • a high-level breakdown of where tokens went
    • an honest assessment of which spend was justified and which was avoidable, tied to specific entries in the summary
    • 2-3 concrete takeaways for future sessions Keep it to observations about this session; do not turn the takeaways into config or instruction changes without being asked.

Notes

  • Deliberately manual-only: an automatic end-of-session run (a SessionEnd hook, possibly gated to long sessions) was considered and deferred - see issue #15. Record a new issue instead of adding a hook here.

Read the full file on GitHub · 52 lines

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.

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 · 52 lines · 47 tokens per session scan A 8c36f2f1ca13

Subscribe to this mod's changes

session-retro is a skill published in the GitHub repository JustinThomas2/agentrc (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 590 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.

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