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 skills add IncommensurableHubris/fullstack-director --skill statusgit 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/status)<a href="https://agentmods.dev/skills/incommensurablehubris/fullstack-director/status"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/status/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/incommensurablehubris/fullstack-director/status"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/status.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 | $0.00237 | $0.04640 |
| Opus 5.5 | $0.00095 | $0.01856 |
| Sonnet 5.5 | $0.00047 | $0.00928 |
| Haiku 4.5 | $0.00024 | $0.00464 |
Grade A, and why
status 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 1mo 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
status · Project GPS — scan, integrity-check, derive, route
The framework's "where am I / what's next" oracle. It is a cross-cutting meta activity (named by function, not
an SDLC seat — prefix-less, like 08-refactor), and per the master plan it is built and run last: it scans
everything, so it is correct only once every other skill's shape is final. Give any project to /status and it
answers three questions from the files on disk — never from memory:
- Is the spine sound? — the integrity verdict (PASS, or FAIL naming the offending REQ-ID).
- What's blocking? — the
pending/deferredamendment + surviving[NEEDS CLARIFICATION]counts that06-releasegates on, surfaced early. - What do I run next? — the single exact next command, in the framework's vocabulary.
Its graded value is not "a nice summary" — a strong reader summarizes a repo too. It is the deterministic derived
state: the integrity verdict + the governance counts + the routed command, computed from the files and emitted
machine-readably into CLAUDE.md § Current State so the next seat — and 06's release gate, and the next /status
— can act on it, not re-derive it.
(2026-07-28, FB-013) status is the propagation contract — name it, don't leave it implied. The framework
propagates by pull: each seat reads a narrow slice, which is what keeps verification isolation auditable and
contexts small. That design has exactly one push channel, and this is it — the only seat whose Reads is a superset
of every other's, and whose write target (CLAUDE.md § Current State) loads into every session automatically.
So: a seat that flips gate-relevant state (a verdict, an amendment row, a release, an audit) routes here before
the next seat — their ## Next skill sections say so — and /06 asserts freshness mechanically at G0 rather
than trusting that someone ran it. Left optional, this channel simply does not run: three weeks of sustained
dogfooding never invoked it once, and every downstream view went stale in exactly the way FB-013 and
FB-014 describe. Optional load-bearing machinery is not load-bearing.
What ships with it
44 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/build_fixture.py 12 KB runs code
- evals/check_status.py 27 KB runs code
- evals/evals.json 14 KB
- evals/fixtures/base/docs/architecture/adr/ADR-001.md 642 B
- evals/fixtures/base/docs/architecture/adr/ADR-002.md 529 B
- evals/fixtures/base/docs/architecture/adr/README.md 339 B
- evals/fixtures/base/docs/architecture/specs/http-api.md 624 B
- evals/fixtures/base/docs/architecture/system.md 1.1 KB
- evals/fixtures/base/docs/design/approved/sprint-02/manifest.md 565 B
- evals/fixtures/base/docs/planning/backlog.md 1.3 KB
- evals/fixtures/base/docs/planning/sprints/sprint-01.md 943 B
- evals/fixtures/base/docs/planning/sprints/sprint-02.md 1.2 KB
- evals/fixtures/base/docs/quality/qa-report-sprint-02.md 550 B
- evals/fixtures/base/docs/README.md 439 B
- evals/fixtures/base/docs/spec/amendment-log.json 659 B
- evals/fixtures/base/docs/spec/architecture-constraints.md 618 B
- evals/fixtures/base/docs/spec/capabilities/api.md 1.3 KB
- evals/fixtures/base/docs/spec/capabilities/digest.md 1.5 KB
- evals/fixtures/base/docs/spec/capabilities/standups.md 686 B
- evals/fixtures/base/docs/spec/design-intent.md 494 B
- evals/fixtures/base/docs/spec/specification.md 2.9 KB
- evals/fixtures/base/src/digest.js 351 B runs code
- evals/fixtures/base/src/server.js 466 B runs code
- evals/fixtures/cases/backlog-gap/.gitkeep 0 B
- evals/fixtures/cases/blocked/docs/spec/amendment-log.json 978 B
- evals/fixtures/cases/blocked/docs/spec/architecture-constraints.md 738 B
- evals/fixtures/cases/corrupted/docs/spec/capabilities/api.md 1.3 KB
- evals/fixtures/cases/healthy/.gitkeep 0 B
- evals/fixtures/cases/patch-deadlock/docs/planning/backlog.md 2.0 KB
- evals/fixtures/cases/patch-deadlock/docs/planning/patches/patch-001.md 964 B
- evals/fixtures/cases/patch-deadlock/docs/planning/patches/patch-002.md 954 B
- evals/fixtures/cases/patch-deadlock/docs/planning/patches/patch-003.md 958 B
- evals/fixtures/cases/patch-deadlock/docs/security/security-audit-sprint-02.md 850 B
- evals/fixtures/cases/patch-in-flight/docs/planning/backlog.md 1.7 KB
- evals/fixtures/cases/patch-in-flight/docs/planning/patches/patch-001.md 962 B
- evals/fixtures/cases/patch-pressure/docs/planning/backlog.md 1.7 KB
- evals/fixtures/cases/patch-pressure/docs/planning/patches/patch-001.md 964 B
- evals/fixtures/cases/patch-pressure/docs/planning/patches/patch-002.md 954 B
- evals/fixtures/cases/patch-pressure/docs/planning/patches/patch-003.md 958 B
- evals/README.md 13 KB
- references/generated-views.md 7.9 KB
- references/integrity-and-governance.md 7.9 KB
- references/next-command.md 13 KB
- templates/current-state.md 798 B
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.
- 1mo ago First seen · 212 lines · 237 tokens per session scan A e6988b52b1eb
status is a skill published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 2mo ago), licensed MIT. It adds 237 tokens to every session and 4,640 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
bmad-agent-pm
Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.
bmad-agent-po
Sofia, the Product Owner: turns any input (an idea, brief, PRD, transcript, notes) into a ticket's requirements, slices initiatives into epics and epics into stories, writes and refines tickets, runs the board, validates the tree, replans when a change lands, and sets up the ticket store. Use when the user asks for…
bmad-retrospective
Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket's story file and plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic…
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-map-codebase
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.
gsd-inbox
Triage and review open GitHub issues and PRs against project templates and contribution guidelines.