Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add crenshawdev/cadence/plugin install cadenceWrote 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/crenshawdev/cadence/cad-assumptions-analyzer-contract)<a href="https://agentmods.dev/skills/crenshawdev/cadence/cad-assumptions-analyzer-contract"><img src="https://agentmods.dev/badge/skills/crenshawdev/cadence/cad-assumptions-analyzer-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/crenshawdev/cadence/cad-assumptions-analyzer-contract"><img src="https://agentmods.dev/badge/skills/crenshawdev/cadence/cad-assumptions-analyzer-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 | $0.00030 | $0.01504 |
| Opus 5 | $0.00015 | $0.00752 |
| Sonnet 5 | $0.00006 | $0.00301 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
cad-assumptions-analyzer-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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job: study the codebase for ONE project phase and surface the decisions a planner would otherwise have to guess at. Back every one with evidence from real files.
<output_format> Group assumptions by area. 2-4 areas is typical - never pad to hit a count. Every assumption carries:
- Decision - the assumption, stated as a decision.
- Certainty - exactly one of
Confident,Likely,Unclear. - Evidence - concrete file paths from this codebase.
- If wrong - the specific outcome, never a vague "could cause problems".
- Alternatives -
LikelyandUnclearitems only: 1-2 other approaches, one line each.
End with a clearly separated section listing topics that need external research. It may be empty - say so if it is.
Skeleton - follow it exactly so the workflow can parse deterministically:
## Assumptions
### Area: <area name>
- **Decision:** <what is assumed, as a decision statement>
**Certainty:** Likely
**Evidence:** `src/exact/path.ts`, `config/other.json`
**If wrong:** <the concrete consequence>
**Alternatives:**
- <alternative approach, one line>
### Area: <next area>
...
## Needs external research
- <topic the codebase cannot answer>: <one line on why>
Omit the Alternatives line for Confident items. Write None. under the research section when nothing qualifies.
</output_format>
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 8af72902aa53
- 4d ago Changed · +1 lines a9433faa0b59
- 9d ago First seen · 96 lines · 30 tokens per session scan A bdf10a54910f
cad-assumptions-analyzer-contract is a skill published in the GitHub repository crenshawdev/cadence (4 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,504 once invoked, about $0.0002 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
branch-and-worktree-workflow
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
git-operations
Git command patterns, branching strategy, and safety protocols. TRIGGER when: managing branches, resolving merge conflicts, or running commit/merge/push operations. SKIP: worktree lifecycle and isolation recovery (use worktree-management); CI automation (use github-actions-template).
dockerized-service-release-deployment-workflow
Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.
coordinate-worktrees-and-threads
Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify repository state outside the coordinator's worktree.
agile-ledger-workspace
Optional multi-repo orchestrator for Agile-Ledger. Install once at a workspace root to manage many repositories at once: discover new repositories on a GitHub org (including ones nobody told you about), clone and bootstrap them, run a single cross-repo "what changed while I was away" sync, and reconstruct undocumented…