edge-tender

edge-tender is a skill for Cursor from seeker71/Coherence-Network. It costs 36 tokens per session (435 once invoked), scanned A, original, Apache-2.0.

A verification skill that checks whether code changes stay within the files and scope defined by a specification.

In plain words
What is it for?
Use it to compare the specification with modified files and produce a PASS or FAIL report with repair guidance.
Why use it?
It catches unrelated edits and shows exactly what needs correction before a merge, meaning the changes are added to the shared codebase.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Install

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.

agentmods
npx agentmods add skills/seeker71/coherence-network/edge-tender
Any agent
npx skills add seeker71/Coherence-Network --skill edge-tender
Clone the repo
git clone --depth 1 https://github.com/seeker71/Coherence-Network

Made for: Cursor.

Wrote 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.

agentmods badge for edge-tender

README.md
[![agentmods](https://agentmods.dev/badge/skills/seeker71/coherence-network/edge-tender.svg)](https://agentmods.dev/skills/seeker71/coherence-network/edge-tender)
Your own site
<a href="https://agentmods.dev/skills/seeker71/coherence-network/edge-tender"><img src="https://agentmods.dev/badge/skills/seeker71/coherence-network/edge-tender.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00435
Opus 5 $0.00018 $0.00217
Sonnet 5 $0.00007 $0.00087
Haiku 4.5 $0.00004 $0.00044

Measured 5d ago against content hash f30b8327cd1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

edge-tender 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.

.cursor/skills/edge-tender/SKILL.md · 45 lines

What it actually says

Edge-Tender Sensing

Quick Start

  1. Read the spec — find "Files to Create/Modify"
  2. List actual changes — which files were modified or created?
  3. Match — each modified file lives inside the spec's edge, or names a finding
  4. Report — PASS or FAIL with each finding

Sensing Checklist

  • Files the spec calls for
  • Files actually modified or created
  • Name each file modified that lives outside the spec's edge

Output Format

PASS: All changes inside the spec's edge.

FAIL: List each finding and provide patch-ready guidance so a follow-up impl/heal can mend without starting from scratch. Use this structure:

  • VERIFICATION_RESULT: FAIL
  • FILES_TO_CHANGE: list of paths that need mending (from spec's Files to Create/Modify or findings)
  • PATCH_GUIDANCE: actionable instructions or minimal diff (file, location, suggested change) for targeted edits
  • Optional: SPEC_VERIFICATION_IMPROVEMENT: when the spec's Verification section is ambiguous, suggest concrete improvement (exact command or steps)

Example FAIL block:

VERIFICATION_RESULT: FAIL
FILES_TO_CHANGE: api/app/routers/foo.py, api/app/services/foo_service.py
PATCH_GUIDANCE: In foo.py line 42, return 404 when id is missing. In foo_service.py, add null check before calling bar().

Suggest: revert the out-of-edge change, or expand the spec to include it. Escalate to needs_decision when human judgment is the right next breath.

Scope

  • Read-only craft. You sense and name; the shaper mends.
  • Spec template: specs/TEMPLATE.md — "Files to Create/Modify" defines the spec's edge.
Changes

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.

  1. 5d ago First seen · 45 lines · 36 tokens per session scan A f30b8327cd1f

Subscribe to this mod's changes

edge-tender is a skill published in the GitHub repository seeker71/Coherence-Network (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 435 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens