A command for changing or inspecting the coding harness's operating mode, including plan-only, automatic, safe, bypass, status, and clear modes.

It helps enable planning without writes, adjust approval settings, view the current mode, or clear a session-specific mode.

It provides a single way to control whether the harness may make changes and to inspect the permissions currently in effect.

mode — Command for Claude Code by 10Legs/freelance-developer-harness

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.

Clone the repo

git clone --depth 1 https://github.com/10Legs/freelance-developer-harness

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/mode/github.svg)](https://agentmods.dev/commands/10legs/freelance-developer-harness/mode)

Your own site

<a href="https://agentmods.dev/commands/10legs/freelance-developer-harness/mode"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/mode/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/10legs/freelance-developer-harness/mode"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,676 The whole file, excluding the scripts and references it only reads on demand.

Security scan F 6 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.02676
Opus 5.5	$0.00006	$0.01070
Sonnet 5.5	$0.00003	$0.00535
Haiku 4.5	$0.00002	$0.00268

Measured 5d ago against content hash 82334ab54a9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade F, and why

mode scanned grade F with 6 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

"Bash(sudo *)",

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

"Read(**/.aws/credentials)",

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

"Bash(curl * | sh*)",

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `cat .claude/sessions/<SESSION_ID>.mode 2>/dev/null || echo "(no session mode)"`

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"Bash(rm -rf *)",

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"Bash(curl * | sh*)",

.claude/commands/mode.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are managing the harness operating mode for: $ARGUMENTS

$ARGUMENTS may be:

plan — session-scoped plan-only mode (no writes, no mutations)
auto — broad auto-approve permissions written to .claude/settings.json (next session)
safe — restore conservative default permissions in .claude/settings.json (next session)
bypass — alias for auto; reminds the user about --dangerously-skip-permissions
status — show current mode (session flag + settings.json snapshot)
clear — remove the session-scoped mode flag

The SESSION_ID is injected into the system prompt as SESSION_ID = <value>. Read it from there; if not present, use "default".

SESSION_ID must match ^[A-Za-z0-9_-]+$. If it does not, stop and report "Invalid SESSION_ID — refusing to construct shell paths."

Steps

If $ARGUMENTS is "status" (or empty):

Run via Bash:
- cat .claude/sessions/<SESSION_ID>.mode 2>/dev/null || echo "(no session mode)"
- jq '.permissions' .claude/settings.json 2>/dev/null || echo "(no permissions block)"

Report in this exact format:

Session mode:    <value or "none">
Settings allow:
  - <each entry on its own line>
Settings deny:
  - <each entry on its own line>
Startup bypass:  Active only if Claude Code was launched with --dangerously-skip-permissions (cannot be toggled mid-session).

Stop.

If $ARGUMENTS is "plan":

Run mkdir -p .claude/sessions via Bash.
Write the string plan to .claude/sessions/<SESSION_ID>.mode using the Write tool.
Tell the user:
- "Session is now in plan mode. I will use the EnterPlanMode tool for any task that would otherwise produce writes, and will present a plan for approval before any mutation."
- "To exit: /mode clear or /mode safe."
Immediately invoke EnterPlanMode for the current turn so the user sees plan output for any in-flight work.
Stop.

If $ARGUMENTS is "clear":

Run rm -f ".claude/sessions/<SESSION_ID>.mode" && echo "cleared <SESSION_ID>.mode" via Bash.
Confirm: "Session mode cleared. Permissions revert to .claude/settings.json defaults."
Stop.

Read the full file on GitHub · 228 lines

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.

5d ago First seen · 228 lines · 16 tokens per session scan F 82334ab54a9e

Subscribe to this mod's changes

mode is a command published in the GitHub repository 10Legs/freelance-developer-harness (33 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 2,676 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it F with 6 findings (asks for root, reaches for credential files, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.

Multi-Agent Productivity agency-workflow ai-agents developer-tools hardware-council

mode

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade F, and why

Asks for rootmediumPrivilege escalation

Reaches for credential fileshighPrivilege escalation

Downloads and executes remote codehighSupply chain

Reads agent configuration directoriesmediumAgent snooping

Recursive force deletehighDestructive command

Makes network callslowCapability

How it starts

Steps

If $ARGUMENTS is "status" (or empty):

If $ARGUMENTS is "plan":

If $ARGUMENTS is "clear":

What this file has done since we first saw it

Other commands, from other repositories

attune

agent

bulk

help

resume

idea