agent-workflow-presets: Skill for Cursor

.cursor/skills/archive-plan/SKILL.md

archive-plan is a skill for Cursor from hlalljie/agent-workflow-presets. It costs 59 tokens per session (1,210 once invoked), scanned A, original, MIT.

A tool for moving a completed project plan from the active plans folder to an archive folder, or restoring an archived plan. The plan's contents and links remain unchanged.

In plain words
What is it for?
Use it when all phases of a plan are complete, or when a previously archived plan needs to become active again.
Why use it?
It keeps active plans separate from finished work without deleting the plan or breaking links inside it.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is hlalljie/agent-workflow-presets's own configuration. It tells Cursor how to work on agent-workflow-presets itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-workflow-presets configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hlalljie/agent-workflow-presets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hlalljie/agent-workflow-presets/main/.cursor/skills/archive-plan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hlalljie/agent-workflow-presets

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 archive-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/archive-plan/github.svg)](https://agentmods.dev/skills/hlalljie/agent-workflow-presets/archive-plan)
Your own site
<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/archive-plan"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/archive-plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for archive-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/archive-plan"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/archive-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,210 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00059 $0.01210
Opus 5.5 $0.00024 $0.00484
Sonnet 5.5 $0.00012 $0.00242
Haiku 4.5 $0.00006 $0.00121

Measured 19d ago against content hash 38c039b03d80, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

archive-plan 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 19d 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/skills/archive-plan/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Archive plan

Where plans live

  • Active: .cursor/plans/<plan-name>/
  • Archived: .cursor/plans-archive/<plan-name>/

The whole folder moves, with the same name and contents, so links inside the plan (tasks to plan.md, plan to research/) keep working. Location is the only state: there is no index and no status field. Moving a plan by hand in either direction is always valid.

When to use

  • The commit skill finishes a plan's last phase and hands off here.
  • The user asks to archive or restore a plan.

Archive

  1. Pick the plan. Use the plan the user or the commit skill named. If none was named, list the plans in .cursor/plans/ whose phases are all complete and ask which.
  2. Check it is complete. Every ## Phase N: heading in plan.md ends — complete, and the Backlog section is empty or absent. If not, list the open phases and stop, unless the user asked to archive it anyway.
  3. Check the target. If .cursor/plans-archive/<plan-name>/ already exists, stop and ask for a different name. Never overwrite or merge.
  4. Find references. Search the repo, excluding .git/ and the plan's own folder, for plans/<plan-name>, matching the whole name (foo must not match foo-bar). Also search the other plans for relative links to it (../<plan-name>/).
  5. Promote what should outlive the plan.
    • Decisions. Read the plan's decisions.md (number it first if it is unnumbered). Any decision that meets the project-decisions rules in workflow.mdc and has no (<plan-name>/D#) line in docs/decisions.md gets a line there now. Create the file if it does not exist.
    • Architecture information. Look through plan.md, research/, and the task files for information about how the system works that is not documented yet: flows, boundaries between parts, contracts, constraints. Skip anything the code or an existing doc already shows. Before writing any of it down, check it is still current against the code and docs/decisions.md. The plan may predate later decisions or changes, so drop or correct whatever no longer holds, and never let the plan's version override newer decisions. Add what remains to the doc it belongs in, following write-docs and the routing in documentation.mdc: docs/folder-structure.md for layout, docs/architecture.md for flows, boundaries, contracts, and constraints (create it from the template if it is missing), docs/runbooks/ for procedures. If the information fits none of those, list the item in the proposal instead of creating a new kind of doc.
  6. Add commit hashes. For each phase whose Completed: line has only a date (skip phases with no such line), find the commit that added — complete to its heading and append its hash, for example Completed: 2026-10-05, 04ecd2d. Run git log -S'<full heading line>' --reverse --format=%h -- .cursor/plans/<plan-name>/plan.md and take the first line of output. If nothing is found (history rewritten, plan copied in from elsewhere), leave the date alone and say so in the proposal.
  7. Move.
    • macOS / Linux: mkdir -p .cursor/plans-archive && mv .cursor/plans/<plan-name> .cursor/plans-archive/<plan-name>
    • Windows: New-Item -ItemType Directory -Force .cursor\plans-archive; Move-Item .cursor\plans\<plan-name> .cursor\plans-archive\<plan-name>

Read the full file on GitHub · 41 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. 19d ago First seen · 41 lines · 59 tokens per session scan A 38c039b03d80

Subscribe to this mod's changes

archive-plan is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 20d ago), licensed MIT. It adds 59 tokens to every session and 1,210 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-10.

Related

Other skills, from other repositories

work-on-ticket

Fetches Jira ticket details, creates an appropriately named branch, and initiates the task planning workflow. Use when the user says "work on [TICKETID]" or similar phrases.

jjmartres/ai-coding-agents · 41 tokens

cast-plan

Turn a request into a plan the team can review before code exists. Explores the codebase, searches prior sessions and recorded decisions for earlier attempts, interviews the user on the open questions, then writes a codecast plan with tasks and dependencies ready for orchestrate. Use when work has several parts, when…

codecast-sh/codecast · 78 tokens

cast-org

Talk through the organization of agents and people around this work with the person, in this session: who reports to whom, what each role looks after, where their sessions go. Reads what the code and the sessions say before it trusts a plan or a task, asks what the records cannot settle, and posts each agreed change…

codecast-sh/codecast · 0 tokens

cast-handoff

Package the current work so the next session or a teammate can continue without reading this thread. Writes the decisions, the direction, what is verified, open questions and ordered next steps as a shared doc, pins the state, and optionally forks, spawns or hands the work to a session. Use before stopping, before a…

codecast-sh/codecast · 77 tokens

cast-loop

Run an autonomous loop that works through a queue of tasks one fresh session at a time, with verification as the gate and a human decision at merge. Sets up a recurring trigger that spawns a session per ready task, a precheck that spends nothing when the queue is empty, and the rules each run follows. Use for a…

codecast-sh/codecast · 94 tokens

cast-conflicts

Before editing or fanning out work, find the live sessions on this repository that are changing the same files, show what they changed, and warn them. Use before starting a task that touches shared files, before spawning workers, or when asked who else is working on this.

codecast-sh/codecast · 59 tokens