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 prime-radiant-inc/greenfield --skill incremental-analysisgit clone --depth 1 https://github.com/prime-radiant-inc/greenfieldWrote 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/prime-radiant-inc/greenfield/incremental-analysis)<a href="https://agentmods.dev/skills/prime-radiant-inc/greenfield/incremental-analysis"><img src="https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/incremental-analysis/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/prime-radiant-inc/greenfield/incremental-analysis"><img src="https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/incremental-analysis.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 | $0.00047 | $0.02084 |
| Opus 5 | $0.00023 | $0.01042 |
| Sonnet 5 | $0.00009 | $0.00417 |
| Haiku 4.5 | $0.00005 | $0.00208 |
Grade A, and why
incremental-analysis 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 9d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incremental Analysis
When a workspace already exists for a target, avoid re-analyzing unchanged sources. Diff the current state against what was previously analyzed and re-analyze only what's stale.
When to Use
This skill activates automatically when /analyze is invoked and a workspace directory already exists at the target path. No --follow flag needed. If the workspace has a .git directory, this is an incremental run. Otherwise, it's a fresh analysis.
Note: --follow is for continuing an interrupted analysis within a single run. Incremental analysis is for subsequent runs against an evolved codebase.
High Water Mark Metadata
Each raw specs tracks the sources it was derived from in YAML frontmatter. This metadata is the basis for incremental diffing.
---
spec_id: SPEC-SESSION-001
derived_from:
- path: workspace/raw/source/analysis/session-module.md
source_ref: a1b2c3d # git SHA of original source file, if available
file_hash: sha256:deadbeef1234 # sha256 of source artifact at analysis time
- path: workspace/public/docs/session-api.md
fetched_at: 2026-04-13T10:00:00Z
url: https://docs.example.com/sessions
- path: workspace/raw/test-evidence/e2e-session-flow.md
file_hash: sha256:cafebabe5678
analyzed_at: 2026-04-13T14:30:00Z
greenfield_version: "2.0"
---
Derived From Entry Types
Each entry in derived_from uses the fields appropriate to its source type:
| Source Type | Required Fields | Optional Fields |
|---|---|---|
| Source code artifact | path, file_hash |
source_ref (git SHA) |
| Web-fetched doc | path, url, fetched_at |
file_hash |
| Runtime observation | path, file_hash |
timestamp in fetched_at |
| Git history | path, source_ref |
file_hash |
| Test evidence | path, file_hash |
-- |
Writing High Water Marks
When writing or updating a raw spec, always include derived_from metadata:
- For source code artifacts: include the git SHA of the original source file (if available) and the sha256 hash of the analysis artifact
- For web-fetched docs: include the fetch timestamp and URL
- For runtime observations: include the observation timestamp
- For test evidence: include the file hash of the evidence artifact
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.
- 9d ago First seen · 199 lines · 47 tokens per session scan A 6d59642343ad
incremental-analysis is a skill published in the GitHub repository prime-radiant-inc/greenfield (273 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,084 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 2026-08-30.
Other skills, from other repositories
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.
analyze
Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…