Borrowing it
Nothing to install: this file belongs to ihuzaifashoukat/splicedeck. 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/ihuzaifashoukat/splicedeck/main/.claude/skills/contributing-to-splicedeck/SKILL.mdgit clone --depth 1 https://github.com/ihuzaifashoukat/splicedeckWrote 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/ihuzaifashoukat/splicedeck/contributing-to-splicedeck)<a href="https://agentmods.dev/skills/ihuzaifashoukat/splicedeck/contributing-to-splicedeck"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/splicedeck/contributing-to-splicedeck/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/ihuzaifashoukat/splicedeck/contributing-to-splicedeck"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/splicedeck/contributing-to-splicedeck.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 | $0.00091 | $0.01183 |
| Opus 5 | $0.00046 | $0.00592 |
| Sonnet 5 | $0.00018 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
contributing-to-splicedeck 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 10d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to splicedeck
AGENTS.md is the contract — twelve hard rules and the table that says which
document owns which concern. It is imported by CLAUDE.md and is not restated
here. Read it. This file is the mechanics.
When two documents disagree
The ownership table in AGENTS.md decides. The owner is right by definition;
edit the other document, never the owner. If code and an owner document disagree,
the code is the bug.
Anything marked Open in an owner document is genuinely undecided. Do not resolve one silently. Raise it, and if you must proceed, write the assumption where a reviewer will see it.
Adding or changing a verb
The CLI and the MCP server are generated from splicedeck/surface/verbs.py.
There is one table and two consumers, and a check asserts they cannot drift.
- Edit the
Verbrow inverbs.py. Never touchterminal.py's parser ormcp.py's tool list — a hand-added tool failstest_surface_parity.py. - Add the handler with
@_impl("<name>")indispatch.py. - Name a return shape in
shapes.py. Everytrimpath must resolve against it. python -m checks.goldento regenerate, and read the diff. A surface change is supposed to be reviewable.- Update
docs/agent-surface.md, which owns the verb table.
Triggers must not share a leading verb phrase — that check exists because overlapping triggers are the failure the table prevents.
Adding a refusal code
A refusal ships with its correction or it does not ship.
alwaysclass:retry_withis non-empty at every construction site.humanclass:needs_humantrue and ahuman_stepof at most 160 characters.- Declare it in the
refusalstuple of every verb that can raise it. The static check walks verb implementations only, so a code raised fromdispatch.callitself needs its own assertion. retry_withtakes a sequence of calls.retry_with=({...})without the trailing comma is a dict,list()of it yields the dict's keys, and the caller receives["verb", "args"]. Five sites shipped that way.python -m checks.skillrefregenerates the catalogue the skills reference.
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.
- 10d ago First seen · 107 lines · 91 tokens per session scan A 4934d3d798c5
contributing-to-splicedeck is a skill published in the GitHub repository ihuzaifashoukat/splicedeck (3 stars, last pushed 23d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,183 once invoked, about $0.0005 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
worktree-isolation
Worktree isolation for parallel agent execution in the pipeline.
git-worktrees
A guide to Git worktrees, which let you check out and work on multiple branches in separate directories at the same time. It includes patterns for isolating parallel coding-agent work.
lore-commit
A Git commit-writing guide that records the reasoning behind a change alongside its commit message. It defines commit types and structured notes for constraints, rejected options, confidence, risk, testing, and follow-up work.
hash-anchored-edit
A file-editing procedure that uses SHA-256 hashes to check whether a file changed before and after an edit. It also describes ownership rules for files handled by parallel agents.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.