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.
curl -O https://raw.githubusercontent.com/hlalljie/agent-workflow-presets/main/.cursor/skills/blueprint/apply/SKILL.mdgit clone --depth 1 https://github.com/hlalljie/agent-workflow-presetsWrote 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.
[](https://agentmods.dev/skills/hlalljie/agent-workflow-presets/apply)<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/apply"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/apply/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.
<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/apply"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/apply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.01351 |
| Opus 5.5 | $0.00025 | $0.00540 |
| Sonnet 5.5 | $0.00012 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
blueprint-apply 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blueprint apply
Bring parts into the current project from a catalog or another project, and later pull updates. Formats, types, sources file, and lock file are in FORMAT.md. Read it first.
Input
A scaffold line (or plain words naming the same things), for example database=postgres-railway@personal, branding=client-x, plan=launch. With no parts named, update every part in .cursor/blueprints.md. focus: <type> limits an update to one type.
Steps
- Sources. Read
~/.blueprints/sources.md. If it is missing, ask for the catalog path and remote once, then create it. - Resolve each part.
- A catalog alias means
parts/<type>/<name>/PART.mdin that catalog. Rungit -C <catalog> pull --ff-onlyfirst; if it fails, continue with the local copy and say so. Clone from the remote if the local path is missing. Read catalog files fromHEAD(git -C <catalog> show HEAD:<path>), not the working tree, so the commit recorded in the lock is exactly what was applied. Mention uncommitted catalog changes if there are any, and ignore them. - A project alias or path means extract on demand (step 3).
- No source given: search catalogs, then project aliases. If nothing or several match, ask.
- A catalog alias means
- Extract (project sources only). Follow "Where to look" in FORMAT.md and build the same fields as a PART.md in memory. Do not write anything into the source project.
- Check before touching files.
- Every
needspart is in this run or already in the lock. touchesoverlaps between parts in this run, or with files, packages, or env names already in the project, are listed as collisions with a proposed merge.- If the spec assumes a different stack than the project uses (for example Tailwind vs CSS modules), translate it. If you cannot, ask.
- Every
- Parts already in the lock are updates. If the catalog has
UPGRADING.md, first show the entries added since the locked commit (git -C <catalog> diff <sha> HEAD -- UPGRADING.md). Then show what changed, one line per commit:git -C <source dir> log --format=%s <sha>..HEAD -- <paths>, where<paths>are the part's files (for a catalog part,parts/<part>plus itsrepo:paths). Skip it when empty, and do not write your own summary. Catalog parts:bash <skill-dir>/../scripts/lock.sh changed <catalog> <part> [repo: paths from the part's Files]; ignore any listed path that the part'sExcludecovers. Project parts: compare the source's current state to its locked commit withgit -C <project> diff <sha> HEAD. Then compare the project to the part. Build one numbered list, one line each, and wait for the user's picks before writing anything:- Pull — the part changed, the project did not. Suggest applying.
- Conflict — both changed. Suggest keep mine, take theirs, or a merged version with the proposed text. For whitelisted files, get the base with
git -C <catalog> show <sha>:<path>and usegit merge-file -p --diff3. Never write conflict markers into project files. - Same — the project already matches the new part. Only the lock needs refreshing; no edit.
- Nothing changed means "up to date". Skip silently.
- No lock line but the target files already exist (a project copied by hand): there is no base, so compare each file two-way and suggest per file. The lock is recorded when done.
- Apply (new parts, and picked update items).
- Implement the Spec in the project's own conventions. Read the nearest existing implementation first, as the repo rules require.
- Copy only whitelisted
Files(repo:entries come from the catalog root; honorExclude). If a target exists, list it as a conflict instead of overwriting. planparts become.cursor/plans/<name>/plan.mdin the draft-plan format, with no tasks.- Packages in
deps: list them for approval and do not install. Env vars: add names to.env.exampleonly; never create.envvalues. - Follow the part's
Applysteps.
- Quick check. Run the project's existing type check or lint if it has one. Do not add tests.
- Lock, once, at the end. For each applied or refreshed part:
bash <skill-dir>/../scripts/lock.sh set <type>/<name> <source> <sha>, where<sha>isgit -C <source dir> rev-parse --short HEAD. Run it from the project root. Do not touch the lock earlier, and do not commit.
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.
- 19d ago First seen · 62 lines · 62 tokens per session scan A e11c3ab30ca4
blueprint-apply is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 20d ago), licensed MIT. It adds 62 tokens to every session and 1,351 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.
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.
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…
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…
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…
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…
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.