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.
npx agentmods add skills/incommensurablehubris/fullstack-director/04-buildernpx skills add IncommensurableHubris/fullstack-director --skill 04-buildergit clone --depth 1 https://github.com/IncommensurableHubris/fullstack-directorWrote 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/incommensurablehubris/fullstack-director/04-builder)<a href="https://agentmods.dev/skills/incommensurablehubris/fullstack-director/04-builder"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/04-builder.svg" alt="Measured on agentmods" 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 | $0.00256 | $0.04360 |
| Opus 5 | $0.00128 | $0.02180 |
| Sonnet 5 | $0.00051 | $0.00872 |
| Haiku 4.5 | $0.00026 | $0.00436 |
Grade A, and why
04-builder 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 5d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
04 · Builder — build
One mode. 04-builder sprint N turns the sprint's realization layer into a working vertical slice + tests and
emits the build-handoff — the sole seed for the context-isolated reviewer (05). Unlike 02/03 (two modes, a
Reconcile gate), 04 is one sequential pass, no gate, no subagents: the isolation that matters is 05's,
downstream. Your graded value is not "working code" (a strong builder writes that too) — it is the
cold-reviewable, honest handoff + non-tautological tests that let a fresh reviewer verify without inheriting your
build bias.
Operating principle — build from realizations, hand off for isolated review
- Build (the funnel). Read
03's per-feature specs + Verification Contracts,02's design contract, the slice's "Done When",system.md/ADRs as the ambient contract. Implementsrc/**sequentially, TDD RED-first for testable behaviors, happy-path (hardening is05). Never re-interpret the raw spine. - Hand off (evidence, not narrative). Emit
_artifacts/exports/build-handoff-sprint-NN.md: a frozen diff baseline + the per-behavior evidence state + a REQ coverage map + attestations, so05can reconstruct the diff, re-run the oracles, and check coverage with zero access to this session. - Non-amender, honest escalator.
04appends noamendment-log.jsonrow (that stays00/02/03/08). It never silently patches code or spec to fake a pass — build-time drift is surfaced and recorded in the handoff.
The flow — one sequential pass (craft lives in the references; load each as its step begins)
- FIX-PASS CHECK — if a FIX REQUIRED
docs/quality/qa-report-sprint-NN.mdexists for this sprint, you are the maker-half of the build↔review loop (05is the checker): read its Findings + the committed reviewer RED tests as an added funnel input and run the fix pass (references/build-discipline.md) — drive each failing behavior to green (make a reviewer RED test pass, never editing it — the anti-circular rule; full TDD-for-bugs for a prose finding), then re-emit the handoff (fixed rows EXECUTED + a deviations note + freshfinal_commit/spec_slice_hash). Scope the pass from the findings ∪ a sweep of every VC row in the in-scope feature specs (each PRESENT, or a disposition row) —/03runs docs-parallel, so a contract can land mid-loop and no input carries it to you (2026-07-28, FB-009). Leave any REQ named inconvergence_firedalone — it survived ≥2 rounds and belongs to/03//00, not to another widen (FB-010). If no such report exists, this is inert — proceed to the normal build. On a fix pass, recordfix_round: N+repeat_findings:in the re-emitted handoff — you read the report,05may not, so this history is the convergence guard's only input (FB-010). PATCH-FUNNEL CHECK — if the dispatch is a certified patch (adocs/planning/patches/patch-NNN.mdrecord with an open## Patchesledger row), the funnel narrows: inputs = the patch record + the existing realizations its owning REQs already have (no new specs, no sprint file); discipline = TDD-for-bugs (reproducing RED test first — the fix ships its regression test); scope = the record's behaviors, nothing wider. Flip the ledger rowplanned → in-progressat build start (your one routine ledger write). The handoff is patch-keyed:_artifacts/exports/build-handoff-patch-NNN.mdwithreview_mode: patch,patch: patch-NNN, andspec_slice_path= the patch record (spec_slice_hashcomputed over it). P3/P4 are HALT conditions: a new dependency (P3) or the certified size budget exceeded (P4) → HALT, mark the ledger rowescalated, re-enter the normal chain — never silently widen. (A small fix arriving here without a patch record? Propose patch classification and route to/01-planner patch— requester ≠ authorizer.) If neither applies, proceed normally. - READ FUNNEL — load the realizations as ambient contract:
docs/architecture/specs/<feature>.md(+ Verification Contracts) ·system.md·docs/architecture/adr/**·docs/design/approved/sprint-NN/manifest.md(if a UI slice) ·docs/design/design-system.md(tokens) ·docs/planning/sprints/sprint-NN.md(the slice + "Done When" + frozen Gherkin) ·.claude/rules/quality-guardrails.md(if present). Direct reads — no Explore subagent (build stays sequential). - CAPTURE
baseline_commit—git rev-parse HEADbefore any edit, into the handoff frontmatter. It anchors the reviewer's exact diff. (Fresh project with no commit? Make the initial commit first, then capture.) - REVIEW VERIFICATION CONTRACTS — for each VC row, confirm it is buildable in this environment. Unbuildable →
INFERRED with a cited reason (e.g. a
browserrow with no runtime) — honest scoping, not silent dropping. This is the builder↔reviewer negotiation. - IMPLEMENTATION ORDER — consume the spec/slice order (foundation → domain → API → UI → wiring). Do not re-derive the slice.
- BUILD (sequential, per behavior) —
references/build-discipline.md:- TDD RED-first, scoped to
unit/api-contractrows: write the test, observe it fail (record it — the anti-tautology capture), minimal code to green, refactor.static-conformance/browserrows use their own oracle. eval-suiterows (Profile: agent-system): eval-first RED — the RED is a failing eval case observed before the fix (the harness over the in-spine dataset is the oracle); and the grader must bite — a degenerate output must fail the grader before the row counts EXECUTED (the bite rule,shared/agentic-profile.md). The handoff's eval-suite row carries both the RED-note and the grader-bites line. Writing a new judge for a row is evals-operations (shared/agentic-profile.md§eval-suite) — its validation record must exist before the row counts EXECUTED.- Anti-tautology gate before marking a row EXECUTED: RED evidence or the introduce-a-bug answer. Reject assertion-free / assert-the-mock / oracle-copied-from-impl tests.
- Reuse-first (read the files a task touches; no duplicate modules) · hardened dependency safety (verify
existence + reputation before install; pin + lockfile + audit; a new dep beyond the envelope is a HALT) ·
outcomes, not ceremony (readable · SRP · no dead code; no SOLID-acronym audit — style is
05/08's seat). Small, atomic conventional commits.
- TDD RED-first, scoped to
- TRACEABILITY — every VC row →
test:loc; every in-scope REQ → FULL/PARTIAL/NONE; every DM-ID (if a manifest) →file:line. - HANDOFF — write the evidence-bearing build-handoff (
references/build-handoff.md·templates/build-handoff.md): frontmatter (baseline_commit/final_commit/spec_slice_path/spec_slice_files/spec_slice_hash/review_mode: sprint— 04 emitssprint|patchonly;fullis 05's all-sprints lane, FB-006; on a fix pass alsofix_round: N+repeat_findings: [REQ ids the report raised in an earlier round too]— 05 cannot read the prior report, so this history is the convergence guard's only input, FB-010) + File List + VC carry-forward (evidence state + repro command + RED-note + oracle hash + every non-EXECUTED reason/Unknown)- the REQ coverage map + attestations. Compute
spec_slice_hashmechanically (the one-liner inreferences/build-handoff.md) so05can recompute + compare — a mismatch is05's BLOCK. Capturefinal_commitlast.
- the REQ coverage map + attestations. Compute
What ships with it
45 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/check_build.py 44 KB runs code
- evals/evals.json 22 KB
- evals/fixtures/base/docs/architecture/adr/ADR-001.md 1.4 KB
- evals/fixtures/base/docs/architecture/adr/README.md 334 B
- evals/fixtures/base/docs/architecture/system.md 4.0 KB
- evals/fixtures/base/docs/spec/capabilities/digest.md 2.1 KB
- evals/fixtures/base/docs/spec/capabilities/standups.md 2.2 KB
- evals/fixtures/base/docs/spec/specification.md 2.9 KB
- evals/fixtures/beacon-build/docs/architecture/specs/research-loop.md 2.0 KB
- evals/fixtures/beacon-build/docs/planning/sprints/sprint-01.md 605 B
- evals/fixtures/beacon-build/docs/spec/agent-contract.md 1.6 KB
- evals/fixtures/beacon-build/docs/spec/amendment-log.json 23 B
- evals/fixtures/beacon-build/docs/spec/architecture-constraints.md 824 B
- evals/fixtures/beacon-build/docs/spec/capabilities/research.md 1.5 KB
- evals/fixtures/beacon-build/docs/spec/evals/research/synthesis.jsonl 153 B
- evals/fixtures/beacon-build/docs/spec/specification.md 1.4 KB
- evals/fixtures/cases/clean-build/docs/architecture/specs/digest-assembly.md 2.8 KB
- evals/fixtures/cases/clean-build/docs/planning/sprints/sprint-01.md 1.9 KB
- evals/fixtures/cases/coverage-traceability/docs/architecture/specs/digest-assembly.md 4.0 KB
- evals/fixtures/cases/coverage-traceability/docs/design/approved/sprint-01/manifest.md 1.2 KB
- evals/fixtures/cases/coverage-traceability/docs/planning/sprints/sprint-01.md 2.6 KB
- evals/fixtures/cases/fix-pass/docs/architecture/specs/digest-assembly.md 2.6 KB
- evals/fixtures/cases/fix-pass/docs/planning/sprints/sprint-01.md 2.1 KB
- evals/fixtures/cases/fix-pass/docs/quality/qa-report-sprint-01.md 4.3 KB
- evals/fixtures/cases/fix-pass/src/digest.js 1.4 KB runs code
- evals/fixtures/cases/fix-pass/test/digest.test.js 1.6 KB runs code
- evals/fixtures/cases/fix-pass/test/review/req-008-grouping.test.js 1.2 KB runs code
- evals/fixtures/cases/patch-budget-exceeded/docs/architecture/specs/digest-assembly.md 2.6 KB
- evals/fixtures/cases/patch-budget-exceeded/docs/planning/backlog.md 1.7 KB
- evals/fixtures/cases/patch-budget-exceeded/docs/planning/patches/patch-001.md 1.7 KB
- evals/fixtures/cases/patch-budget-exceeded/docs/planning/sprints/sprint-01.md 2.1 KB
- evals/fixtures/cases/patch-budget-exceeded/src/digest.js 1.2 KB runs code
- evals/fixtures/cases/patch-budget-exceeded/test/digest.test.js 1.8 KB runs code
- evals/fixtures/cases/patch-build/docs/architecture/specs/digest-assembly.md 2.6 KB
- evals/fixtures/cases/patch-build/docs/planning/backlog.md 1.7 KB
- evals/fixtures/cases/patch-build/docs/planning/patches/patch-001.md 1.7 KB
- evals/fixtures/cases/patch-build/docs/planning/sprints/sprint-01.md 2.1 KB
- evals/fixtures/cases/patch-build/src/digest.js 1.2 KB runs code
- evals/fixtures/cases/patch-build/test/digest.test.js 1.8 KB runs code
- evals/fixtures/cases/unbuildable-contract/docs/architecture/specs/digest-assembly.md 3.5 KB
- evals/fixtures/cases/unbuildable-contract/docs/planning/sprints/sprint-01.md 2.5 KB
- evals/README.md 13 KB
- references/build-discipline.md 18 KB
- references/build-handoff.md 13 KB
- templates/build-handoff.md 9.1 KB
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.
- 5d ago First seen · 166 lines · 256 tokens per session scan A c5c26398847c
04-builder is a skill published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 25d ago), licensed MIT. It adds 256 tokens to every session and 4,360 once invoked, about $0.0013 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.
Other skills, from other repositories
gsd-plan-review-convergence
Cross-AI plan convergence - replan until review concerns are resolved.
gsd-ns-manage
Route to the appropriate management skill based on the user's intent. gsd-config (settings + advanced + integrations + profile) and gsd-workspace (new + list + remove) are post-#2790 consolidated entries.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
spec-kitty-spdd-reasons
Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.