skill-update

skill-update is a command for Cursor from phuoctrung-ppt/ai-sdlc-workflow. It costs 35 tokens per session (352 once invoked), scanned A, original, MIT.

A command that runs a full review of project retrospectives to look for repeated lessons and propose updates to the project's skills and memory files. A retrospective is a record of what went well, went wrong, or was learned during earlier work.

In plain words
What is it for?
Use it after project work when you want to inspect retrospectives, record durable decisions or gotchas, and prepare a skill-update proposal.
Why use it?
It turns recurring lessons into proposed guidance instead of leaving them buried in past notes. Proposed skill changes remain subject to approval before they are applied.

Command for Cursor

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/phuoctrung-ppt/ai-sdlc-workflow/skill-update
Clone the repo
git clone --depth 1 https://github.com/phuoctrung-ppt/ai-sdlc-workflow

Made for: Cursor.

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 skill-update

README.md
[![agentmods](https://agentmods.dev/badge/commands/phuoctrung-ppt/ai-sdlc-workflow/skill-update.svg)](https://agentmods.dev/commands/phuoctrung-ppt/ai-sdlc-workflow/skill-update)
Your own site
<a href="https://agentmods.dev/commands/phuoctrung-ppt/ai-sdlc-workflow/skill-update"><img src="https://agentmods.dev/badge/commands/phuoctrung-ppt/ai-sdlc-workflow/skill-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 352 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 $0.00035 $0.00352
Opus 5 $0.00017 $0.00176
Sonnet 5 $0.00007 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 4d ago against content hash 7896bb447704, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-update 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 4d 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.

.cursor/commands/skill-update.md · 43 lines

What it actually says

Skill Update (Learning Layer)

Act as Orchestrator. Dispatch the learning loop (does not implement product features).

Do not open .cursor/state/** or .aisdlc/*.json.

Steps

  1. Ensure Memory layer files exist:

    • docs/retrospective.md
    • docs/memory/decisions.md, gotchas.md, shortcuts.md
  2. Dispatch @learning-agent with an explicit full pass:

python3 .cursor/context/context-builder.py \
  --phase review \
  --task "skill update full pass from retrospective" \
  --agent learning-agent \
  --keywords "retrospective,pattern,skill,learning,gotcha,shortcut" \
  --budget 5000
  1. Agent must follow skill skill-updater:

    • Identify patterns from retrospective (≥2 signals)
    • Write proposal to docs/reviews/YYYY-MM-DD-skill-update-proposal.md or report no pattern
    • Update memory files when facts are durable
    • Do not apply SKILL.md patches until you approve
  2. Present proposal to human/orchestrator:

    • Approve → agent applies patch, marks APPLIED
    • Reject → leave PENDING or close with reason

Notes

  • This command is the explicit full Learning entrypoint.
  • /dev-module Phase 6 only does lightweight distillation + a short learning-agent scan.
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. 4d ago First seen · 43 lines · 35 tokens per session scan A 7896bb447704

Subscribe to this mod's changes

skill-update is a command published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 18d ago), licensed MIT. It adds 35 tokens to every session and 352 once invoked, about $0.0002 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.