session-report

session-report is a skill for Claude Code, Codex from Codagent-AI/agent-skills. It costs 54 tokens per session (944 once invoked), scanned A, original, MIT.

A session-review guide that checks an agent’s work for hidden assumptions and missing context. It asks the reviewer to connect each finding to evidence, risk, and a recommended human decision.

In plain words
What is it for?
Retrospectives, execution-quality audits, assumption reviews, and documenting risks that require human follow-up.
Why use it?
It exposes choices that were not specified by the task and may have affected the result.

Skill for Claude CodeCodex

Part of the codagent plugin — 27 skills shipped together

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/codagent-ai/agent-skills/session-report
Any agent
npx skills add Codagent-AI/agent-skills --skill session-report
Clone the repo
git clone --depth 1 https://github.com/Codagent-AI/agent-skills

Made for: Claude Code, Codex.

Or install codagent, the plugin that ships this one along with the rest of its 27 skills.

Wrote 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.

agentmods badge for session-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/codagent-ai/agent-skills/session-report.svg)](https://agentmods.dev/skills/codagent-ai/agent-skills/session-report)
Your own site
<a href="https://agentmods.dev/skills/codagent-ai/agent-skills/session-report"><img src="https://agentmods.dev/badge/skills/codagent-ai/agent-skills/session-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 944 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 $0.00054 $0.00944
Opus 5 $0.00027 $0.00472
Sonnet 5 $0.00011 $0.00189
Haiku 4.5 $0.00005 $0.00094

Measured 3d ago against content hash e14049dfdfb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-report 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 3d 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.

skills/session-report/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Report

Audit your own session against the task file(s) you were given. Surface assumptions you made and context gaps that caused struggles. These are observations for the human — not things you can fix after the fact.

Review Process

Work through each dimension in order. For every finding, cite specific evidence.

Dimension 1: Assumption Audit

Identify every place you made a decision that was not dictated by the task file or spec. For each assumption:

  • Ambiguity — what the spec didn't say
  • Choice — what you decided and why (the reasoning, not just the outcome)
  • Risk — what could go wrong if this choice is wrong. Be specific: name the scenario, the affected code path, and what would break. "Could surprise future workflows" is not specific enough — say which workflow shape triggers it and what the symptom would be.
  • Impact classification:
    • benign — reasonable default, no real consequence (do not report)
    • notable — meaningful choice that could have gone differently
    • risky — could cause problems, warrants review
  • Recommendation — what the reviewer should do: verify behavior, add a test, clarify the spec, or approve as-is with rationale.

Report only risky and notable assumptions. Drop benign entirely — they dilute the signal. Sort risky first, then notable.

Dimension 2: Context Gaps

A context gap is a major, avoidable hole in the task file or project context that sent you down a fundamentally wrong path, caused you to build the wrong thing, or wasted significant effort that better upfront information would have prevented entirely.

The bar is high. Most sessions have zero context gaps. Fixing a linter warning is not a context gap. Searching for a convention is not a context gap. Iterating on validator feedback is not a context gap — it is the normal development loop.

Examples of real context gaps:

  • The task said to extend module X, but module X was deleted last week and replaced by module Y — you built against a nonexistent target
  • The task required integrating with service A but didn't mention that service A requires an auth token from a separate provisioning step — you couldn't have known this without tribal knowledge
  • The task file pointed you to the wrong directory or package, wasting significant effort before you found the right one

Read the full file on GitHub · 83 lines

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. 3d ago First seen · 83 lines · 54 tokens per session scan A e14049dfdfb2

Subscribe to this mod's changes

session-report is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 944 once invoked, about $0.0003 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 2026-08-30.

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