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 adilkalam/orca --skill search-before-editgit clone --depth 1 https://github.com/adilkalam/orcaWrote 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/adilkalam/orca/search-before-edit)<a href="https://agentmods.dev/skills/adilkalam/orca/search-before-edit"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/search-before-edit/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/adilkalam/orca/search-before-edit"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/search-before-edit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.01191 |
| Opus 5.5 | $0.00014 | $0.00476 |
| Sonnet 5.5 | $0.00007 | $0.00238 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
search-before-edit 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 1mo 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Before Edit
MANDATORY: Always search/grep before modifying ANY file. This prevents breaking existing patterns and ensures changes fit the codebase.
The Rule
Before editing ANY file, you MUST:
- Search for existing usage patterns
- Understand the file's context
- Check for related code that may need updates
Required Searches
Before Creating New Code
DO:
- Search for similar existing implementations
- Check if the functionality already exists
- Look for established patterns in the codebase
- Find related files that might be affected
# Example: Before creating a new button component
grep -r "Button" src/components/
grep -r "btn-" src/styles/
grep -r "button" src/ # case variations
Before Modifying Existing Code
DO:
- Search for all usages of what you're changing
- Find imports/exports of the modified code
- Identify dependent files
- Check for tests that might need updates
# Example: Before renaming a function
grep -r "oldFunctionName" .
grep -r "from.*module-with-function" .
grep -r "oldFunctionName" **/*.test.*
Before Deleting Code
DO:
- Search for ALL references to the deleted code
- Check for dynamic imports or string references
- Verify nothing will break
- Look for documentation references
# Example: Before deleting a component
grep -r "ComponentName" .
grep -r "component-name" . # kebab-case
grep -r "componentName" . # camelCase
Search Strategies
Multiple Query Wording
Run multiple searches with different terms. First-pass results often miss key details.
# Don't just search once
grep -r "authentication"
# Also try variations
grep -r "auth"
grep -r "login"
grep -r "session"
grep -r "signin"
grep -r "sign-in"
Semantic First, Then Specific
Start with broad, high-level queries, then narrow down:
- Broad: "authentication flow"
- Medium: "verifyToken"
- Exact: function signature or unique string
Check Related Files
When modifying a file, check its neighbors:
- Same directory siblings
- Import sources
- Test files (
*.test.*,*.spec.*) - Type definition files (
*.d.ts,types.ts) - Story files (
*.stories.*) - Documentation
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.
- 1mo ago First seen · 208 lines · 35 tokens per session scan A 16f23538500c
search-before-edit is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,191 once invoked, about $0.0001 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…