performance-review

performance-review is a command for coding agents from SaigonXIII/evc. It costs 0 tokens per session (695 once invoked), scanned A, original, MIT.

A weekly review command for checking how published social-media content performed against its plan.

In plain words
What is it for?
Use it to check whether five planned posts were published, the intended audiences were reached, the story developed as planned, and which posts received impressions, likes, reposts, or replies.
Why use it?
It brings the week's planned posts, exported content, and available X metrics into one review before the next planning cycle.

Command

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/saigonxiii/evc/performance-review
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc

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 performance-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/saigonxiii/evc/performance-review.svg)](https://agentmods.dev/commands/saigonxiii/evc/performance-review)
Your own site
<a href="https://agentmods.dev/commands/saigonxiii/evc/performance-review"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/performance-review.svg" alt="Measured on agentmods" height="20"></a>
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 695 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 $0.00695
Opus 5 $0.00000 $0.00347
Sonnet 5 $0.00000 $0.00139
Haiku 4.5 $0.00000 $0.00069

Measured 3d ago against content hash eebbcd710ed3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-review 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.

_templates/commands/performance-review.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Review

Weekly performance analysis of published content. Run on Friday PM or Monday AM before planning.

Trigger

User invokes /content-review or asks to "review this week's content", "how did our posts perform", "content analysis"

Arguments

  • Optional: week number (e.g., /content-review W13). Defaults to current week.

Steps

1. Gather Published Content

Read the output folder for the specified week:

  • content-engine/output/[week]/
  • If no output folder exists, check brand/templates/social/exports/ for recent exports
  • Read any X copy, LinkedIn copy, and banner files produced

2. Analyze Against Plan

Read the week's brief from content-engine/calendar/ and check:

  • Did we execute all 5 planned posts?
  • Did we hit the right audience segments per day?
  • Did the narrative arc hold (each post building on the previous)?
  • Any posts that deviated from the plan? Why?

3. Pull Live X Metrics

Fetch engagement data for the last 7 days of {{SOCIAL_HANDLE_X}} posts using whichever metrics surface the user has wired:

  • If an X/Twitter MCP is installed: call its metrics/analytics tools to pull per-tweet impressions, likes, retweets, replies, and engagement rate.
  • If the X API is wired via another integration: use that.
  • Otherwise: prompt the user to paste the week's metrics (from X Analytics) or to enable a metrics integration before continuing.

You need per-tweet impressions, likes, retweets, replies, engagement rate, and the top-performing post.

Then:

  • Match tweets to content calendar days by created_at date
  • Rank posts by engagement rate
  • Identify which pillar/audience/template performed best
  • Compare against previous weeks if past review files exist in content-engine/calendar/
  • Calculate week-over-week trends (impressions, engagement rate)
  • Flag any day that had no post (missed schedule)

4. Narrative Arc Review

  • Read the past 2-3 weeks of content briefs
  • Assess whether the overall narrative is building and compounding
  • Identify gaps: are we over-indexing on one pillar or audience?
  • Suggest the narrative direction for next week

Read the full file on GitHub · 74 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 · 74 lines · 0 tokens per session scan A eebbcd710ed3

Subscribe to this mod's changes

performance-review is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 695 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.