construct
Implement an existing sealed `blueprint.md`; run its Verification; report completion, incomplete verification, or contradiction; skip planning-required work.
How do I install this agent skill?
npx skills add https://github.com/akshay-diwadkar/first-four-hours --skill constructIs this agent skill safe to install?
- Gen Agent Trust Hubfail
The skill executes arbitrary shell commands defined within the input Markdown 'blueprint' files. This design allows for command execution and potential data exfiltration if the input file is malicious or comes from an untrusted source, making it highly vulnerable to indirect prompt injection.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Construct
Authority
Construct persists no execution state and creates no execution artifact. Blueprint owns every planning decision; Git worktree state owns the implementation delta. Discovery is evidence, not authority: it cannot expand a sealed Blueprint. The Blueprint stays byte-for-byte unchanged. Preserve unrelated dirty work; execution requires a Git worktree. Scripts prove mechanics only; the agent owns attribution, scope truth, and completion.
Command
python <construct>/scripts/cli.py --repo-root <repo> --input blueprint_file=<blueprint.md> --input phase=before --format json verify
Judge criteria first; follow next_command when present, else required_action.
Smooth execution loop
- Intake. Read Execution contract once, then run
verifybefore for fresh work,statusfor resume. For dirty targets, non-Git paths, concurrent, destructive, or recovery work read Safety. Read the whole Blueprint before editing; when a caller quotes or paraphrases it, reread that step and work from its sealed text. Each turn re-reads your context, so issue independent reads and checks together, calling alone only when the input depends on an earlier result. - Implement each
### N.in order.applywrites declared blocks, never by hand: withRed:,applyFrozen, write prose tests,proveits declared red, thenapplyExact. Implement the rest, thenprovegreen with the caller-held next unused attempt and follow its forward guidance. Repair only what Blueprint settles; otherwise stop asplan-contradiction. - Verify. Run
verifyphaseafter; judge everyExpect:. Execute Runs only throughverifyorreverify, on resume too. Repair locally only when Blueprint fixes the answer, thenreverifyfrom the earliest invalidated Run line. A shown declaredIncomplete:outcome ends asverification-incompleteafter step 4. Else stop with plan-contradiction evidence. Timeout or mutation failures are unsafe, neverreverify. - Reconcile and report. Compare the final diff against the sealed Blueprint once, per the Execution contract. Consequential behavior or safety risk, meaningful propagation, indirect verification, or a hard-to-observe acceptance condition earns an Earned Conformance Review; else none. Report instructions, each Proof run and Run with its
Expect:and quoted output showing whether it met it, unrecoverable red gaps, notices, any caller quote the Blueprint lacks, whether a review was earned, run, or earned and not run, and whether protected paths and HEAD are unchanged.
Exceptions
Stopping ends the Construct run: plan-contradiction, protected-work-conflict, or safety-contradiction, reported with exact evidence. Failure, resume, and stopping owns failing Runs, resume, and what happens next.
Final and stop reports end with one optional next step fitting this outcome, after a stop its recovery owner's: a fenced, self-contained prompt naming any repository, issue, PR, or artifact it needs, or say none is needed. Only a "yes" starts it, via any skill it names, but the user runs a charter, diagnose, or ticket step as its /<skill> command.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/akshay-diwadkar/first-four-hours/construct">View construct on skillZs</a>