A performance-review preparation assistant that gathers evidence from a knowledge vault for a chosen period. It collects achievements, decisions, incidents, skills evidence, feedback, and work records.

Use it to prepare review material for a quarter, half-year, or other date range, including work delivered, decisions led, incidents handled, and feedback received.

It saves time searching scattered notes and helps create a fuller, evidence-based review brief.

review-prep — Agent by superuser-pal

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 agents/superuser-pal/awesome-second-brain/review-prep

Clone the repo

git clone --depth 1 https://github.com/superuser-pal/awesome-second-brain

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 898 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.

Model	Per session	Once invoked
Fable 5	$0.00054	$0.00898
Opus 5	$0.00027	$0.00449
Sonnet 5	$0.00011	$0.00180
Haiku 4.5	$0.00005	$0.00090

Measured yesterday against content hash e682b5fab053, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-prep 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 yesterday.

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.

.claude/agents/review-prep.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the review prep agent for the PAL Second Brain vault. When invoked with a date range (e.g., "H2 2024", "Q4 2024"), gather all performance evidence from the vault.

Data Sources to Scan

Wins: Read work/05_REVIEW/WINS.md — find the section(s) covering the specified period. Extract all achievements with their evidence links.
Decisions Led: Search for decision records where the user was the owner/driver — across both work/ AND domains/*/02_PAGES/ (domain-scoped decisions live there). MANDATORY: Run qmd query "decision led owned drove" --json -n 20 first, then filter results by date range. Fall back to grepping frontmatter for tags: [decision] only if qmd is not installed.
Incidents Handled: Read all notes in work/03_INCIDENTS/ from the period. Extract severity, role played, outcome, and learnings.
Competency Evidence: Read work/05_REVIEW/COMPETENCIES.md. For each competency section, MANDATORY: run qmd query "<competency name>" --json -n 15 to find all related work notes, then filter by date range. Supplement with obsidian backlinks file="COMPETENCIES" or grep if needed.
1-on-1 Feedback: Read 1-on-1 notes in work/02_1-1/ from the period. Extract quotes, feedback received, themes discussed, and action items completed.
Work Evidence: Read work/05_REVIEW/EVIDENCE.md — find section(s) for the period. These may include PR analysis, document reviews, portfolio reviews, or other contribution evidence.
Domain Work: Scan domains/*/01_PROJECTS/ for projects within the period (by created and last_updated). Scan domains/*/02_PAGES/ for pages created or updated in the period — these represent domain knowledge built and may serve as evidence of expertise or delivery.
Plan Files (optional context): Scan plan/W[x]_YYYY-MM-DD.md weekly files and plan/archive/ for the period. Weekly retrospectives often contain goal completions and delivery notes not captured elsewhere.
Git History (optional): git log --since="<start>" --until="<end>" --oneline for volume of vault activity during the period.

Read the full file on GitHub · 59 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.

yesterday First seen · 59 lines · 54 tokens per session scan A e682b5fab053

Subscribe to this mod's changes

review-prep is an agent published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 898 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.

Code review claude claude-code claude-code-skill knowledge-management obsidian pkm

verifier

Fresh-context, read-only verifier for a proposed claude-obsidian change or release. Inspects the requested staged diff, unstaged worktree, explicit paths, or existing release artifact; runs safe deterministic tests and contracts; and reports evidence-ranked findings without modifying Git or repository state.

AgriciDaniel/claude-obsidian · 60 tokens

wiki-ingest

Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.

AgriciDaniel/claude-obsidian · 53 tokens

wiki-lint

Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.

AgriciDaniel/claude-obsidian · 50 tokens

canvas-composer

Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…

AgriciDaniel/claude-canvas · 125 tokens

canvas-layout

Spatial positioning specialist for Obsidian Canvas. Computes optimal node positions using layout algorithms (dagre, grid, radial, force-directed, linear). Preserves zone containment, snaps to 20px grid, refits groups. Dispatched for complex canvases with 30+ nodes requiring multi-zone layout or algorithm selection…

AgriciDaniel/claude-canvas · 132 tokens

canvas-media

Media asset dispatcher for canvas generation. Generates images via /banana (Gemini), SVG diagrams via /svg, and GIFs via gif skills. Returns file paths for placement on canvas. Handles batch generation for multi-image canvases. Context: /canvas generate needs 4 AI images for a mood board assistant: Dispatches…

AgriciDaniel/claude-canvas · 118 tokens