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 agentmods add skills/sjarmak/agent-workflows/constraint-inversionnpx skills add sjarmak/agent-workflows --skill constraint-inversiongit clone --depth 1 https://github.com/sjarmak/agent-workflowsWrote 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/sjarmak/agent-workflows/constraint-inversion)<a href="https://agentmods.dev/skills/sjarmak/agent-workflows/constraint-inversion"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/constraint-inversion.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02303 |
| Opus 5 | $0.00000 | $0.01151 |
| Sonnet 5 | $0.00000 | $0.00461 |
| Haiku 4.5 | $0.00000 | $0.00230 |
Grade A, and why
constraint-inversion 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 5d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraint Inversion — What-If Removal. Takes a design with stated constraints and spawns N agents, each removing or inverting ONE constraint to explore what becomes possible without it, then synthesizes findings into a constraint dependency map that reveals which constraints are truly load-bearing vs merely assumed.
Arguments
$ARGUMENTS — format: [N] [path/to/design.md or inline description] where N is optional constraint-removal agent count (default: 5, min 3, max 7)
Parse Arguments
Extract:
- agent_count: the optional leading integer (default 5, min 3, max 7)
- input: path to a design document, architecture doc, PRD, or project plan — or an inline description of the design and its constraints
If the input is missing or unclear, ask the user to clarify before proceeding.
Phase 1: Extract and Confirm Constraints
If a file path is given: read it and extract every stated or implied constraint — technical, organizational, temporal, financial, compatibility, and operational.
If inline: parse the description for the same.
Prepare a design brief that includes:
- What is being built (one paragraph summary)
- Key design decisions already made
- Dependencies (internal and external)
Then prepare a constraint inventory — a numbered list of every constraint found. For each constraint:
- Name: short label (e.g., "Backward compatibility with v2 API")
- Type: one of Technical, Organizational, Financial, Temporal, Compatibility, Operational, Regulatory
- Source: where the constraint comes from (explicit requirement, assumed convention, inherited from prior decision, regulatory, etc.)
- Current impact: how this constraint shapes the design today
Present the design brief and constraint inventory to the user. Ask:
- Are any constraints missing from this list?
- Are any listed constraints actually already relaxed or negotiable?
- Which N constraints should agents remove? (Or let the skill auto-select the N most design-shaping ones.)
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.
- 5d ago First seen · 213 lines · 0 tokens per session scan A 669eae92a743
constraint-inversion is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,303 tokens. 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
speckit.clarify
Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.
speckit.specify
Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.
update-docs
Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…
docker-compose-first-install
Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.
speckit.plan
Skill "speckit.plan" from caipe-io/ai-platform-engineering, covering user input, outline, phases, phase 0: outline & research and phase 1: design & contracts.
speckit.sync-template
Skill "speckit.sync-template" from caipe-io/ai-platform-engineering, covering user input, outline, step 1 — read current state, step 2 — discover latest release and step 3 — read the manifest.