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 ngocsangyem/MeowKit --skill sprint-contractgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/sprint-contract)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/sprint-contract"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/sprint-contract/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/ngocsangyem/meowkit/sprint-contract"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/sprint-contract.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 | $0.00074 | $0.02891 |
| Opus 5 | $0.00037 | $0.01445 |
| Sonnet 5 | $0.00015 | $0.00578 |
| Haiku 4.5 | $0.00007 | $0.00289 |
Grade A, and why
mk:sprint-contract scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. Per AC check: **Testable?** (probable via browser/curl/CLI) **Rubric-aligned?** (binding matches content) **Scope clear?** (no ambiguity) How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mk:sprint-contract — File-Based Sprint Contract Protocol
Negotiation protocol between generator and evaluator. Produces a signed contract file at tasks/contracts/{date}-{slug}-sprint-{N}.md BEFORE the generator writes any source code. Enforced by gate-enforcement.sh (Phase 4 extension).
For single-task plan validation (cook flow), use
mk:validate-planinstead.mk:sprint-contractis for product-level specs feeding intomk:autobuildonly.
When to Use
Activate when:
- User runs
/mk:sprint-contract <action> [task-slug] - Harness (Phase 5) needs to negotiate a sprint before invoking the generator
- Generator agent needs to read a signed contract before starting implementation
- A previously signed contract needs amendment due to mid-build scope discovery
Skip when:
MEOWKIT_AUTOBUILD_MODE=LEAN(adaptive density bypass for COMPLEX/Opus 4.6 tier)- The plan is
--fastmode (overhead exceeds value) - The task is
/mk:fix simple(Gate 1 already bypassed; contract bypass too)
Subcommands
| Subcommand | Owner | Effect |
|---|---|---|
propose |
generator (developer agent) | Drafts a contract from the product spec + rubric preset; status: draft → negotiating |
review |
evaluator | Critiques the proposed contract for testability + scope clarity; produces clarification requests |
amend |
generator | Iterates on the contract per evaluator feedback; status stays negotiating; rounds += 1 |
sign |
both | Both agents commit to the contract via git commit messages; status: negotiating → signed |
validate |
anyone | Runs validate-contract.sh to check schema conformance |
sprint-goal |
user | Writes/reads/aligns sprint-LEVEL goal in tasks/contracts/sprint-state-{date}-sprint-{N}.md (Agile mode) |
Workflow (Inline — monolithic, < 150 lines)
propose (generator)
- Read active product spec from newest
tasks/plans/*/plan.md - Load rubric preset via
mk:rubric/scripts/load-rubric.sh --preset {preset} - Determine sprint
N: max of existingtasks/contracts/*-{slug}-sprint-*.md+ 1, default 1 - Copy
assets/contract-template.md→tasks/contracts/{YYMMDD-HHMM}-{slug}-sprint-{N}.md - Populate: 5–15 ACs in Given/When/Then form, each bound to one preset rubric, each with a Verification line. Every preset rubric should have ≥1 AC binding
- Set frontmatter:
status: negotiating,rounds: 0,created: {YYMMDD-HHMM} - Run
validate-contract.sh; fix and re-validate until clean - Print:
"Contract proposed at {path}. Awaiting evaluator review."
What ships with it
5 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.
- 9d ago First seen · 178 lines · 74 tokens per session scan A 4ff03a194524
mk:sprint-contract is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,891 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
phx-work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after phx-plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
lab:autoresearch
Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.