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 commands/1mcp-app/agent/targetgit clone --depth 1 https://github.com/1mcp-app/agentWhat 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 | $0.00014 | $0.00653 |
| Opus 5 | $0.00007 | $0.00327 |
| Sonnet 5 | $0.00003 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
target 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Target Context Commands
Runtime Target Contexts are verified, named runtime endpoints. A named context can carry locally saved bearer credentials; an ephemeral --url connection cannot. Use a context for repeatable remote workflows.
1mcp target <subcommand> [options]
Add and Select
1mcp target add <name> <url> [options]
1mcp target use <name> [options]
target add verifies the Runtime Identity endpoint before storing the target.
add:--use,--display-name <label>,--ca-file <path>,--insecure-skip-verify,--replace,--accept-new-identity.use:--accept-insecure-tls,--json.
Security: --insecure-skip-verify disables TLS certificate verification, and --accept-insecure-tls confirms continued use of that unsafe setting. Both remove protection against man-in-the-middle attacks. Prefer --ca-file; use the insecure flags only for a target whose identity you have verified independently.
1mcp target add prod https://mcp.example.com/mcp --use
1mcp target add staging https://mcp.example.com/mcp --ca-file ./company-ca.pem
Inspect and Verify
1mcp target current
1mcp target list
1mcp target inspect <name>
1mcp target verify <name> [--accept-insecure-tls] [--json]
current and list do not contact a runtime. verify confirms the saved target identity.
Import, Export, and Repair
1mcp target export [--output <file>]
1mcp target import <file> [--dry-run] [--json]
1mcp target doctor [--fix-secrets] [--prune-orphans]
Use - as the import file to read a bundle from stdin. doctor --fix-secrets repairs local secret-store permissions; --prune-orphans removes credential references for missing targets.
Rename and Delete
1mcp target rename <old> <new>
1mcp target delete <name> [--force]
delete --force also permits deletion of the current context.
Use a Context
The --context <name> selector is implemented by instructions, inspect, run, and proxy:
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 · 81 lines · 14 tokens per session scan A 202b148f6a05
target is a command published in the GitHub repository 1mcp-app/agent (494 stars, last pushed 4d ago), licensed Apache-2.0. It adds 14 tokens to every session and 653 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 2026-08-30.
Other commands, from other repositories
go
MCP tool management and workflow proxy.
review-and-fix
Reviews a PR or staged changes and automatically initiates a Pickle Fix loop for findings.
pr-review
Review a specific pull request.
frontend
Injects context of all relevant cli files.
cleanup-back-to-main
Go back to main and clean up the branch.
explore-network
Explore the current TouchDesigner network and report its structure.