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 alonf/specrew --skill multi-artifact-governance-principle-embeddinggit clone --depth 1 https://github.com/alonf/specrewWrote 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/alonf/specrew/multi-artifact-governance-principle-embedding)<a href="https://agentmods.dev/skills/alonf/specrew/multi-artifact-governance-principle-embedding"><img src="https://agentmods.dev/badge/skills/alonf/specrew/multi-artifact-governance-principle-embedding/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/alonf/specrew/multi-artifact-governance-principle-embedding"><img src="https://agentmods.dev/badge/skills/alonf/specrew/multi-artifact-governance-principle-embedding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00027 | $0.01355 |
| Opus 5 | $0.00014 | $0.00678 |
| Sonnet 5 | $0.00005 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
multi-artifact-governance-principle-embedding 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 6d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
When embedding a critical governance principle (like plain-language-first or jargon-early detection), do not rely on a single artifact or checklist. Instead, embed the principle into multiple complementary artifacts so that even if one gets skipped, outdated, or misunderstood, the principle survives in the others.
Iteration 001 (feature 007) discovered this pattern when codifying the governance-acronym detection rule (three-or-more governance acronyms in lead without plain-language paraphrase). The rule was embedded in:
- Coordinator prompt (T001): Plain-language guardrail + examples showing how to lead with human terms
- Handoff template (T002): Concrete copy-paste patterns demonstrating plain-language-first structure
- Governance checklist (T005): Soft-warning check operationalizing the detection rule
- Soft-validator design (T006): Pseudo-code and algorithmic definition of the detection logic
This four-artifact redundancy ensures that:
- Agents reading only the prompt get the guardrail and examples
- Reviewers reading only the template see validated patterns
- Governance reviewers reading only the checklist get the detection rule
- Implementers reading only the validator design get the algorithmic definition
No single document path leads to the principle being skipped.
Patterns
- Map the principle to its owners. Identify which roles (agents, reviewers, implementers, governance) interact with the principle. Embed guidance in artifacts those roles naturally read.
- Separate implementation guidance from detection rules. Agents need to understand "how to do it" (prompt + template). Governance tools need to understand "how to detect violations" (checklist + validator). Both groups benefit from the same principle but consume different artifact forms.
- Use redundancy strategically. Don't duplicate word-for-word. Instead, express the principle at different levels of abstraction:
- Prompt: Plain human guidance with examples ("Do not open with three or more acronyms without first explaining them")
- Template: Concrete copy-paste patterns showing compliant and non-compliant forms
- Checklist: Operationalized check ("Count governance acronyms in lead. If ≥3 and no paraphrase, flag as soft warning")
- Validator design: Algorithmic definition with pseudo-code and edge cases
- Verify coverage before governance publication. Before closing an iteration, search for the principle across all artifacts. Verify it appears in at least 2-3 independent artifact types. Single-artifact principles are fragile.
- Document the multi-artifact strategy in the feature spec or plan. Make explicit that "this principle is embedded in X, Y, Z artifacts" so future maintainers know which documents to update if the principle needs refinement.
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.
- 6d ago First seen · 78 lines · 27 tokens per session scan A 29b807f4df4c
multi-artifact-governance-principle-embedding is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,355 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.