build
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
How do I install this agent skill?
npx skills add https://github.com/juliusbrussee/cavekit --skill buildIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill implements a build and test loop that interprets instructions from local specification files. While performing its intended function, it creates a surface for indirect prompt injection because it relies on the content of SPEC.md to determine which files to edit and which shell commands to execute as verification.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
build — implement spec
Single-thread native plan→execute. You are main Claude. No swarm.
LOAD
- Read
SPEC.md. If missing → tell user to invoke the spec skill first. Stop. - Read
FORMAT.mdonce if not loaded. - Read §R if present — external facts the build must honor, ⊥ re-derive or contradict.
- Parse invocation args:
§T.n→ that task only--next→ lowest-numbered row with status.or~--allor empty → every.row in §T order
High blast radius (shared module, auth, data, money, public §I)? Run /review first. Trivial & reversible? Skip planning ceremony, just do step EXECUTE.
PLAN
Native plan mode — you delegate to it, you do not reinvent task breakdown. For chosen task(s):
- Cite every §V invariant that applies. Plan must respect all.
- Cite every §I interface touched. Plan must preserve shape.
- List files to create / edit.
- Verification contract — name the EXACT test(s) / acceptance criteria that prove each §V touched. Which test, not "add tests". "Do TDD" alone backfires; the spec says what to check. Each §V touched → a named test that fails first.
- Name verification command (test, build, lint) — this is the external oracle. Green = done; ⊥ "looks done".
Show plan. Wait for user OK unless auto mode.
EXECUTE
Per task in order:
- Flip §T.n status cell
.→~. Just write to SPEC.md. - Edit code per plan.
- Run verification command.
- Pass → flip
~→x. Next task. - Fail → invoke backprop skill. Do NOT retry blindly.
FAIL → BACKPROP
On test/build failure:
- Read failure output.
- Ask: is failure (a) my code bug, (b) spec wrong, or (c) unspecified edge case?
- If (a) → fix code, re-run. No spec change.
- If (b) or (c) → invoke spec skill with
bug: <cause>first, let it update §V and §B, then resume build against updated spec.
Rule: never silently fix root-cause without considering backprop. §B is the memory that stops recurrence.
WRITE POLICY
- Only flip §T status. No other SPEC.md edits from build.
- Other spec edits → invoke spec skill.
- Commit after each §T completes. Message:
T<n>: <goal line>+ §V cites.
VERIFICATION
Task x only if:
- Verification command (the oracle) exits 0.
- Every §V touched has its named test from the verification contract, and it passes.
- No §V invariant regressed (run full test suite at end).
NON-GOALS
- No sub-agents. No parallel workers. Main thread only.
- No progress dashboards.
cat SPEC.md | grep §Tis the dashboard. - No speculative work beyond chosen task scope.
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/juliusbrussee/cavekit/build">View build on skillZs</a>