Borrowing it
Nothing to install: this file belongs to sponge-b0b/Polaris. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sponge-b0b/Polaris/main/.agents/skills/spec-contract/SKILL.mdgit clone --depth 1 https://github.com/sponge-b0b/PolarisWrote 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/sponge-b0b/polaris/spec-contract)<a href="https://agentmods.dev/skills/sponge-b0b/polaris/spec-contract"><img src="https://agentmods.dev/badge/skills/sponge-b0b/polaris/spec-contract.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.04799 |
| Opus 5 | $0.00013 | $0.02400 |
| Sonnet 5 | $0.00005 | $0.00960 |
| Haiku 4.5 | $0.00003 | $0.00480 |
Grade A, and why
spec-contract 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 2d 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 — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Contract
$spec-contract is an internal, non-lifecycle helper for $verify-spec and $review-spec.
It owns two shared facts that must not be independently reinvented by those callers:
- the complete Spec Contract Manifest of normative obligations;
- the complete Spec Change Provenance universe separating branch-local, mixed-provenance, inherited-only, and unchanged/named repository surfaces.
It does not verify implementation, review implementation, create findings, mutate tracker state, edit repository files, commit, push, decide remediation, or decide semantic lifecycle ownership from Git position. A caller-supplied temporary contract-handoff file is permitted working state, not a repository artifact.
Change Provenance Is Not Semantic Ownership
This section is authoritative and supersedes every preserved section below that equates branch-local Git history with Spec-owned or Mixed semantic ownership.
The deterministic provenance helper and this skill may establish only where a repository change sits relative to the fixed Spec baseline, current HEAD, and immutable default-branch head. They must not infer that a change is owned by the current Spec merely because it is reachable only from the Spec branch.
Canonical repository provenance states are:
- branch-local — changed on the current branch relative to the immutable default-branch head and not also changed by inherited default-branch integration;
- mixed-provenance — the same surface changed in both inherited default-branch history and current branch-local history;
- inherited-only — present in fixed-baseline →
HEADintegration history but absent from the current branch-local delta; - unchanged/named — unchanged by the branch but explicitly named by a Spec obligation or governing authority and therefore potentially relevant to proof.
The complete branch/integration surface universe must be materialized before callers reason about scope. Every provenance candidate must appear in exactly one mechanical provenance state; missing/ambiguous provenance fails closed.
What ships with it
2 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.
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.
- 2d ago Changed · +41 lines 412653213ac8
- 4d ago Changed · +36 lines 43d5f1ba1671
- 8d ago First seen · 385 lines · 26 tokens per session scan A cc1c014c0588
spec-contract is a skill published in the GitHub repository sponge-b0b/Polaris (4 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 4,799 once invoked, about $0.0001 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…