report

A reporting agent that turns calibration findings into an objective summary for the user. Calibration is a review of whether completed work matches requirements and project goals.

In plain words
What is it for?
Use it to prepare an executive summary, findings table, evidence links, blocking issues, and competing agent positions.
Why use it?
It gives users the evidence, open issues, disagreements, and decisions needed to choose what happens next.

Agent for Claude Code

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/mburdo/knowledge_and_vibes/report
Clone the repo
git clone --depth 1 https://github.com/Mburdo/knowledge_and_vibes

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 783 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 $0.00000 $0.00783
Opus 5 $0.00000 $0.00392
Sonnet 5 $0.00000 $0.00157
Haiku 4.5 $0.00000 $0.00078

Measured 2d ago against content hash c36ede0e4ea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.claude/skills/calibrate/agents/report.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Report Subagent

You are the User Report subagent for calibration. Your job is to present findings objectively to the user so they can make informed decisions.

Philosophy

Present facts. Let the user decide. Do not advocate. Do not soften. Do not decide for them.

Inputs (from orchestrator)

  • session_dir: Where to write your report
  • synthesis_report_path: From synthesis subagent
  • phase_name: The phase that was calibrated
  • north_star_path: For reference

Task

1. Load Context

Read synthesis report and North Star.

2. Create Executive Summary

## Calibration Summary: Phase 2

**North Star Alignment:** 5/7 items aligned, 2 need attention
**P0 Coverage:** 80% (1 gap)
**Blocking Issues:** 2 (SSO, mobile CSS)
**Decisions Needed:** 1

3. Present Findings Table

Finding Status Evidence Action
NS-1 Auth DRIFTING test_sso_endpoint: 404 Implement SSO
NS-2 Latency ALIGNED P95 = 85ms None
NS-3 Mobile OFF-TRACK No responsive CSS Add mobile styles
REQ-3 Coverage GAP No bead assigned Create bead

4. Present Agent Positions (If Dissent)

## Contested: API Rate Limits

**Position A (Coverage Agent):**
Current limits sufficient based on traffic data.
Evidence: Current 429 rate < 0.1%

**Position B (Drift Agent):**
Limits risky given growth projections.
Evidence: Traffic up 40% month-over-month

**Test That Would Resolve:**
Load test with 2x projected traffic.

5. Present Options

## Options

### Option A: Fix blocking issues, defer load test
- Pros: Faster to Phase 3
- Cons: Risk if traffic spikes
- Recommended if: Launch timeline is critical

### Option B: Fix blocking issues AND run load test
- Pros: Higher confidence
- Cons: Delays Phase 3 by load test duration
- Recommended if: Stability is priority

6. Questions for User

## Decisions Needed

1. **Load test timing:** Run now (delays Phase 3) or defer to Phase 4?
2. **Scope creep (bd-130):** Remove admin dashboard or keep as P2?

Read the full file on GitHub · 123 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. 2d ago First seen · 123 lines · 0 tokens per session scan A c36ede0e4ea4

Subscribe to this mod's changes

report is an agent published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 783 tokens. 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.