ops-retro

ops-retro is a command for coding agents from tjboudreaux/cc-plugin-text-visualizations. It costs 18 tokens per session (2,147 once invoked), scanned A, original, MIT.

A command for reviewing a product team's work over a chosen period using issue-tracking data.

In plain words
What is it for?
Use it for a weekly retrospective, where a team looks back at delivery progress and identifies process improvements.
Why use it?
It gathers opened and completed issues, work speed, backlog change, and issue-type breakdowns in one review.

Command

Part of the text-visualizations plugin — 5 skills, 3 commands 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 commands/tjboudreaux/cc-plugin-text-visualizations/ops-retro
Clone the repo
git clone --depth 1 https://github.com/tjboudreaux/cc-plugin-text-visualizations

Or install text-visualizations, the plugin that ships this one along with the rest of its 5 skills, 3 commands.

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 ops-retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/tjboudreaux/cc-plugin-text-visualizations/ops-retro.svg)](https://agentmods.dev/commands/tjboudreaux/cc-plugin-text-visualizations/ops-retro)
Your own site
<a href="https://agentmods.dev/commands/tjboudreaux/cc-plugin-text-visualizations/ops-retro"><img src="https://agentmods.dev/badge/commands/tjboudreaux/cc-plugin-text-visualizations/ops-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,147 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 5.1 $0.00018 $0.02147
Opus 5 $0.00009 $0.01073
Sonnet 5 $0.00004 $0.00429
Haiku 4.5 $0.00002 $0.00215

Measured 5d ago against content hash cbcfd0496e32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ops-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 5d 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.

commands/ops-retro.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly Ops Retrospective

Run a structured retrospective using bd/bv to analyze velocity, health trends, and identify improvement opportunities.

Arguments: $ARGUMENTS

Parse arguments:

  • --since: Time period to analyze (default: "7 days ago")
  • --output: Output format (default: markdown)

Retrospective Agenda

1. Period Summary

Get the diff for the analysis period:

SINCE="${SINCE:-7 days ago}"

# Full diff
DIFF=$(bv --robot-diff --diff-since "$SINCE" --json)

echo "=== Retrospective: $SINCE to now ==="
echo "$DIFF" | jq '{
  period: .period,
  closed: (.closed_issues | length),
  opened: (.new_issues | length),
  net_change: ((.closed_issues | length) - (.new_issues | length))
}'

2. Velocity Analysis

# Velocity metrics
CLOSED=$(echo "$DIFF" | jq '.closed_issues | length')
OPENED=$(echo "$DIFF" | jq '.new_issues | length')
VELOCITY=$(echo "scale=2; $CLOSED / ($OPENED + 0.001)" | bc)

echo "## Velocity"
echo "- Closed: $CLOSED"
echo "- Opened: $OPENED"
echo "- Ratio: $VELOCITY (>1.0 is good, reducing backlog)"

# Breakdown by type
echo "\n### By Type"
echo "$DIFF" | jq '.closed_issues | group_by(.type) | .[] | {type: .[0].type, count: length}'
echo "$DIFF" | jq '.new_issues | group_by(.type) | .[] | {type: .[0].type, count: length}'

Interpret:

  • Velocity > 1.0: Reducing backlog (healthy)
  • Velocity < 1.0: Growing backlog (may need intervention)
  • Velocity ~ 1.0: Maintaining (sustainable)

3. What We Accomplished

# Completed work
echo "## Completed"
echo "$DIFF" | jq -r '.closed_issues[] | "- [\(.id)] \(.title) (P\(.priority))"'

# Group by priority
echo "\n### By Priority"
echo "$DIFF" | jq '.closed_issues | group_by(.priority) | .[] | {priority: .[0].priority, count: length, issues: [.[].id]}'

4. What We Started

# New issues created
echo "## New Issues"
echo "$DIFF" | jq -r '.new_issues[] | "- [\(.id)] \(.title) (P\(.priority), \(.type))"'

# Discovered work (scope creep indicator)
echo "\n### Discovered During Work"
bd list --json | jq -r '[.[] | select(.notes != null and (.notes | contains("discovered-from")))] | .[] | "- [\(.id)] \(.title)"'

Read the full file on GitHub · 274 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. 5d ago First seen · 274 lines · 0 tokens per session scan A cbcfd0496e32

Subscribe to this mod's changes

ops-retro is a command published in the GitHub repository tjboudreaux/cc-plugin-text-visualizations (2 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 2,147 once invoked, about $0.0001 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.