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 paulnsorensen/easy-cheese --skill moldgit clone --depth 1 https://github.com/paulnsorensen/easy-cheeseWrote 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/paulnsorensen/easy-cheese/mold)<a href="https://agentmods.dev/skills/paulnsorensen/easy-cheese/mold"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/mold/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/paulnsorensen/easy-cheese/mold"><img src="https://agentmods.dev/badge/skills/paulnsorensen/easy-cheese/mold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00182 | $0.03436 |
| Opus 5 | $0.00091 | $0.01718 |
| Sonnet 5 | $0.00036 | $0.00687 |
| Haiku 4.5 | $0.00018 | $0.00344 |
Grade A, and why
mold 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 today.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mold
Ceremony scales to the job. The Bounds pass picks one of three tiers from references/tiers.md: Quick writes a one-confirm mini-spec, Light runs only the dialogue modes the open forks need, and Full runs the whole Flow below. /cheese's tier-1 escalation enters mini-spec mode with no confirm; see ## Agent-invoked mini-spec mode.
Flow
- Bounds pass — open the
Goal / Decided / Asking / [AGENT-DECIDED]ledger with the goal pinned as one sentence; only an explicit user fork changes it. Map every input's goals and non-goals as one[AGENT-DECIDED]line; ask the user only when the goal is genuinely unknown or a leverage trigger fires. Run the shape check, then announce the tier with its reason (references/tiers.md). Quick exits here: one fast confirm, then## Agent-invoked mini-spec mode. Upgrade the tier whenever the evidence changes; never downgrade silently. - Route — choose the secondary mode from
references/modes.md, announce it, and correct false premises first. - Dialogue — consequential forks are the user's to pick. A fork is consequential per the leverage line in
../age/references/voice.md. Every other fork is[AGENT-DECIDED]. Supply options, trade-offs, and evidence before you ask. Ground each critical claim through code, the Validate Cycle, or a Prototype Cycle. Resolve every contradiction. Render the decision map after three consecutive fork questions, or on request. - Sketch — For work across modules or with a new public interface, run
references/shape-check.md. Bind identity and role nouns to code referents. Record the Placement block; no bodies. - Plan for approval — run the fresh-context fork-coherence taste test with
python3 skills/mold/scripts/mold.pyz taste-testand persist its digest-bound pass; a failure reopens only named forks, and the third failed verdict stops. Light with one expected curd stops here: no planner, and the handoff is/cook --auto <spec-path>. Otherwise dispatch a typedPlannerRequest, validate itsPlannerResultWriterView(one retry, then stop before the handshake), normalize on the host, and persist only the typedPlannerResultandCurdPlan. A legacy projection needs an explicit migration request and must be lossless orUnsupportedProjection. Present the plan's semantic curds and waves at the handshake. Seereferences/curdle.md§ "Pre-approval typed planner dispatch". - Two-key handshake — Before extraction, the user and agent must agree to the draft spec and displayed typed plan. The user provides an explicit verb. The agent performs a coherence self-check. Neither key changes nor disappears. See
references/handshake.md. - Curdle — Resolve the durable spec path with
SPEC=$(python3 skills/mold/scripts/mold.pyz artifact-path specs <slug>). Phase one writes the local artifact and write-ahead prepared state before any external call. It writes the approved spec at"$SPEC". It also writes the host-validatedPlannerResultandCurdPlan. It also writes local issue drafts and the session's non-obvious decisions as durable ADRs. Phase two publishes approved follow-ups. Retain the prepared recovery state when an external capability is unavailable or publication fails. Phase two reconciles their state and references into the durable spec before any handoff. - Publish and hand off — after reconciliation, run
python3 skills/mold/scripts/mold.pyz curd-count. Then publish the approvedCurdPlanwithpython3 skills/mold/scripts/mold.pyz publishand keep the returnedHandoffPointerpath; Light with one curd skips publish and hands/cook --auto <spec-path>. Prompt through## Handoff. Dispatch only the user's non-stop selection.
What ships with it
19 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.
- phase-contract.yaml 286 B
- references/adr.md 3.9 KB
- references/commands.md 1.1 KB
- references/context-budget.md 4.5 KB
- references/curd-count.md 5.2 KB
- references/curdle.md 23 KB
- references/evals.md 4.4 KB
- references/gate-graph.md 4.8 KB
- references/grounding.md 5.1 KB
- references/handoff-menus.md 2.3 KB
- references/handshake.md 18 KB
- references/mini-spec-mode.md 5.2 KB
- references/modes.md 10 KB
- references/prototype-cycle.md 3.3 KB
- references/shape-check.md 5.8 KB
- references/tiers.md 4.1 KB
- references/validate-cycle.md 2.4 KB
- scripts/mold.dot 3.9 KB
- scripts/mold.pyz 1545 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.
- today Changed · +4 tokens per session efd4923fca2a
- 3d ago Changed · -2 lines · +27 tokens per session 53c7fb87e31a
- 10d ago First seen · 155 lines · 151 tokens per session scan A 0a3be56b0141
mold is a skill published in the GitHub repository paulnsorensen/easy-cheese (18 stars, last pushed today), licensed MIT. It adds 182 tokens to every session and 3,436 once invoked, about $0.0009 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
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
graphql-contract-review
Review a GraphQL schema and a Backend-for-Frontend (BFF) contract BEFORE implementation, against a GraphQL-specific checklist: schema shape and nullability (null-bubbling), errors-as-data unions, N+1 and DataLoader, query cost and depth limits, cursor-connection pagination, federation entity ownership, breaking-change…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.