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/juliusbrussee/cavekit/specnpx skills add JuliusBrussee/cavekit --skill specgit clone --depth 1 https://github.com/JuliusBrussee/cavekitWhat 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 | $0.00149 | $0.00978 |
| Opus 5 | $0.00075 | $0.00489 |
| Sonnet 5 | $0.00030 | $0.00196 |
| Haiku 4.5 | $0.00015 | $0.00098 |
Grade A, and why
spec 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 3d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec — spec mutator
Read FORMAT.md at repo root if not already loaded. Caveman skill applies to all writes here.
DISPATCH
Inspect user request and project state:
- No
SPEC.mdat repo root AND args describe idea → NEW - No
SPEC.mdANDfrom-codein args → DISTILL SPEC.mdexists AND args startbug:→ BACKPROPSPEC.mdexists AND args startamend→ AMENDSPEC.mdexists, no args → ask user which mode
INPUTS — spec is the sole mutator
The other verbs produce material; spec writes it. Ingest their handoff blocks into the right section, show a diff, write on OK:
- grill → sharpened §G + §C
- research → §R rows (add the §R section if absent)
- review → drafted §V lines + the risk verdict
- deepen → §I/§V/§T amendments
⊥ rewrite a section the handoff did not name. Sectioned ownership (see FORMAT.md).
NEW — idea → spec
Input: user idea. If it arrived fuzzy, prefer running grill first.
Steps:
- Extract goal (1 line, caveman). → §G.
- List constraints user stated or implied. → §C.
- List external surfaces user named. → §I.
- §R only if research ran — else omit the section (right-size).
- Propose initial invariants. → §V (numbered V1…).
- Break goal into ordered tasks. → §T pipe table, all status
., ids T1… - §B section with header row only (
id|date|cause|fix).
Write to SPEC.md. Show user full file. Ask: "spec OK? /review if high-blast-radius, else /build."
DISTILL — code → spec
Walk repo. Produce §G (infer from README/package.json/main entry), §C (infer from stack), §I (enumerate public APIs/CLIs/configs), §V (derive from tests and assertions), §T (one task per known TODO or missing test), §B (empty).
Caveman everywhere. Flag uncertain items with ? in text so user can confirm.
BACKPROP — bug → §B + §V
Input: bug: <description>.
Steps:
- Parse bug description.
- Find root cause (read relevant code).
- Decide: would a new invariant catch recurrence? If yes → draft
V<next>. - Append §B row:
B<next>|<date>|<cause>|V<N>. - Append new invariant to §V.
- If fix also changes behavior → add/update §T rows.
- Show diff. Apply only on user OK.
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.
- 3d ago First seen · 96 lines · 149 tokens per session scan A 99361ddf25a6
spec is a skill published in the GitHub repository JuliusBrussee/cavekit (1,141 stars, last pushed 19d ago), licensed MIT. It adds 149 tokens to every session and 978 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.
workflow-start
Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…
release-archivist
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
spec-writer
Create or refine spec-superflow planning artifacts. Invoke when the change is understood well enough to write proposal.md, specs/, design.md, and tasks.md.
contract-builder
Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.