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/nick-railsback/skill-engine/new-referencenpx skills add nick-railsback/skill-engine --skill new-referencegit clone --depth 1 https://github.com/nick-railsback/skill-engineWhat 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 | $0.00033 | $0.01721 |
| Opus 5 | $0.00016 | $0.00860 |
| Sonnet 5 | $0.00007 | $0.00344 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
new-reference 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New reference
Create a new primary reference file from scratch and wire it into the navigator's catalog. Use this when a single topic has been identified ahead of time and a full discover pass would be overkill.
The proposal stages (into $CTX_PROPOSED/, never the live tree):
- A new file under
references/<source-slug>-<topic>.md(the reference itself) — manifest statusadded. - A new row in the navigator's catalog table at
SKILL.mdpointing at that reference — manifest statusmodified(the liveSKILL.mdis copied into$CTX_PROPOSED/copy-on-write, then the row is added there).
It does NOT write to research/.research-state.json — that file is a binary
setup marker only. If the new reference covers a topic from an
as-yet-unregistered source, the source is added to
research/source-paths.json (status modified, same copy-on-write seed) as
part of the same proposal. Every other file in the contextualizer is recorded
unchanged. The whole proposal lands live only when the user runs
/skill-engine:apply <name>.
For kind: git-managed sources, the proposed entry follows the same
omit-on-default convention as engine-bootstrap Step 2.4: branch is
recorded only when the contextualizer follows a non-default branch
(dev, nonprod, release/v2); absent ⇒ HEAD. NEW does not prompt
for a branch at registration time — the maintainer can supply
"branch": "<name>" in the proposed entry directly during the
approval gesture, or edit source-paths.json after approval. Field
schema and regex enforcement: 02-artifact-contract.md §"source-paths.json entry shape".
For web-doc sources, citations pin three values: source_url (from the
fetched URL), content_hash (sha256(file)[:8]), and crawl_date (ISO-8601
UTC). The cache path is the model's read path but is NOT the citation
target — a reviewer on a different machine verifies by re-fetching the URL
and comparing content_hash.
Contextualizer root
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 First seen · 139 lines · 33 tokens per session scan A 05d2ac9e64c6
new-reference is a skill published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 25d ago), licensed MIT. It adds 33 tokens to every session and 1,721 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
skill-creator
Create or improve Zhin Agent skills (SKILL.md). Use when asked to add a skill, write SKILL.md, document a repeatable agent workflow, or refine skill frontmatter/keywords. Triggers: 创建技能, 写 SKILL, skill-creator, 加 skill.
skill-sync-checker
Detects content drift between skill files and their source documents. Helps maintain skills that are derived from other documentation by comparing content and flagging outdated sections.
tech-design-generation
Generates professional Technical Design Documents following industry-standard engineering practices. This skill activates when the user asks to write a technical design, create an architecture design, draft a design doc, write a technical proposal, do system design, create a technical design document, write an RFC…
test-cases-generation
Generates structured test case sets with multi-dimensional coverage from project code analysis or specification documents. This skill activates when the user asks to write test cases, generate tests, supplement tests, create test coverage, or improve test completeness. It auto-scans the project to extract testable…
erpaval
Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…
idea
Use when exploring a new idea before writing formal specifications. Guides users through iterative discovery, research, and critical analysis to crystallize vague ideas into validated requirement drafts. Includes anti-pseudo-requirement checks, competitive research, demand evidence gathering, and "What if we don't…