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 00-discoverygit 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/00-discovery)<a href="https://agentmods.dev/skills/incommensurablehubris/fullstack-director/00-discovery"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/00-discovery.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 | $0.00222 | $0.05445 |
| Opus 5 | $0.00111 | $0.02722 |
| Sonnet 5 | $0.00044 | $0.01089 |
| Haiku 4.5 | $0.00022 | $0.00545 |
Grade A, and why
00-discovery 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 7d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
00 · Discovery — specify
Produce the spec spine (docs/spec/): the single source of declaration-truth every later skill references.
Whatever the user brings — a comprehensive spec, a thin brief, or just an itch — turn it into a complete, traceable
spine, then emit the per-project AGENTS.md.
Operating principle — fidelity-adaptive ingestion
Trust what the source evidences; spend interrogation only where it is thin. Ingest whatever the user gives you (treat a provided doc as truth-by-default for what it covers), then let a fidelity assessment decide how much to ask: a near-truth spec flows through almost silently; a thin one earns a real interview; no doc at all means a full interview. You don't pick a "mode" — the doc's quality sets the depth. This mirrors gold-standard spec-driven development: ingest, then clarify only the underspecified.
You own the declaration half of the old product-backlog role (requirements + acceptance). Build planning —
epics, sprints, the backlog ledger — is /01-planner's; never write a backlog or sprint here.
Modes — one front door
The operating principle above governs the default /00-discovery (a doc or a formed idea). Sibling invocations
handle other starting materials; all converge on the same CHALLENGE → FIDELITY → GATE → WRITE-SPINE machinery —
only the ingest source and the spine-writing rule differ. Pick by what the user brings:
| Invocation | When (starting material) | Writes spine? | Flow |
|---|---|---|---|
/00-discovery |
a doc, PRD, brief, or a formed idea | yes (after the gate) | the phases below (default) |
/00-discovery explore |
a bare itch, pre-commitment ("brainstorm", "explore an idea", "I have an itch") | never — hard-gated | references/explore-divergence.md |
/00-discovery adopt |
an existing codebase with no spine ("adopt this codebase", "reverse-engineer a spec") | yes (after the gate) | references/adopt-evidence.md |
/00-discovery reflect |
the amendment backlog | via the write-path | the reflect section below |
What ships with it
34 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_spine.py 26 KB runs code
- evals/evals.json 13 KB
- evals/fixtures/adopt-mini/notekeep/__init__.py 106 B runs code
- evals/fixtures/adopt-mini/notekeep/auth.py 1.6 KB runs code
- evals/fixtures/adopt-mini/notekeep/cli.py 1.7 KB runs code
- evals/fixtures/adopt-mini/notekeep/export_pdf.py 1.1 KB runs code
- evals/fixtures/adopt-mini/notekeep/store.py 917 B runs code
- evals/fixtures/adopt-mini/README.md 840 B
- evals/fixtures/adopt-mini/tests/test_auth.py 627 B runs code
- evals/fixtures/agent-brief/brief.md 1.7 KB
- evals/fixtures/rich-spec/PRD.md 2.3 KB
- evals/fixtures/security-flavored/brief.md 972 B
- evals/fixtures/thin-spec/brief.md 394 B
- evals/fixtures/undefended-bet/spec.md 1.5 KB
- evals/README.md 8.3 KB
- references/adopt-evidence.md 5.6 KB
- references/challenge-2x2.md 3.7 KB
- references/explore-divergence.md 4.6 KB
- references/requirements-authoring.md 9.0 KB
- references/review-gate.md 2.2 KB
- templates/agents-view.md 2.9 KB
- templates/charter.md 1.7 KB
- templates/claude-bridge.md 505 B
- templates/gemini-bridge.md 329 B
- templates/hooks/pre-commit.sample 825 B
- templates/hooks/spine-verify.yml 599 B
- templates/scripts/verify-spine.py 22 KB runs code
- templates/SECURITY.md 1.5 KB
- templates/spec/agent-contract.md 4.1 KB
- templates/spec/amendment-log.json 23 B
- templates/spec/architecture-constraints.md 4.0 KB
- templates/spec/capabilities/_EXAMPLE.md 2.3 KB
- templates/spec/design-intent.md 1.6 KB
- templates/spec/specification.md 6.7 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.
- 7d ago First seen · 249 lines · 222 tokens per session scan A 0db1a0140261
00-discovery is a skill published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 27d ago), licensed MIT. It adds 222 tokens to every session and 5,445 once invoked, about $0.0011 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-audit-milestone
Audit milestone completion against original intent before archiving.
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.
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.