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.
git clone --depth 1 https://github.com/10Legs/freelance-developer-harnessWrote 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/commands/10legs/freelance-developer-harness/use-client)<a href="https://agentmods.dev/commands/10legs/freelance-developer-harness/use-client"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/use-client/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/commands/10legs/freelance-developer-harness/use-client"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/use-client.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 | $0.00010 | $0.01065 |
| Opus 5.5 | $0.00004 | $0.00426 |
| Sonnet 5.5 | $0.00002 | $0.00213 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
use-client 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are activating the client context lock for: $ARGUMENTS
$ARGUMENTS may be:
<project-slug>— lock to a project by name alone; client is resolved automatically (e.g.storefront)<client-slug>— lock to a client with no specific project (e.g.acme-corp)<client-slug> <project-slug>— lock to a project explicitly (e.g.acme-corp storefront)clearorreset— remove the lock for this sessionlist— show all active session locks
Steps
If $ARGUMENTS is "list":
- Run
ls .claude/sessions/*.client 2>/dev/null || echo "(none)"via Bash to find all client lock files. - For each file found, print the session ID (filename without
.client) and its contents. - Confirm: "Active client locks listed above."
- Stop here.
If $ARGUMENTS is "clear" or "reset":
- The SESSION_ID is injected into the system prompt as
SESSION_ID = <value>. Read it from there; if not present, use "default". - Run
rm -f ".claude/sessions/<SESSION_ID>.client" && echo "cleared <SESSION_ID>.client"via Bash. - Confirm: "Client lock cleared for this session."
- Stop here.
Otherwise:
-
Parse the arguments:
- First token = FIRST_ARG
- Second token (optional) = SECOND_ARG
-
Resolve CLIENT_SLUG and PROJECT_SLUG:
Case 0 — full path provided (
clients/<client-slug>/projects/<project-slug>):- If FIRST_ARG matches the pattern
clients/*/projects/*, extract CLIENT_SLUG and PROJECT_SLUG from the path segments. - Validate
clients/<CLIENT_SLUG>/projects/<PROJECT_SLUG>/exists as a directory. If not, stop and tell the user. - Proceed to step 3.
Case A — two tokens provided (
<client-slug> <project-slug>):- CLIENT_SLUG = FIRST_ARG, PROJECT_SLUG = SECOND_ARG
- Validate by running
ls clients/<CLIENT_SLUG>/projects/<PROJECT_SLUG>/via Bash. If it fails, stop and tell the user.
Case B — one token provided:
- First check if
clients/FIRST_ARG/exists as a directory (runls clients/FIRST_ARG/via Bash) → it's a client-only lock. CLIENT_SLUG = FIRST_ARG, no PROJECT_SLUG. - Otherwise, search for a project by running
ls clients/*/projects/FIRST_ARG/via Bash (or Globclients/*/projects/FIRST_ARG/— note: use Bash ls for directory matching).- If exactly one match is found: extract CLIENT_SLUG from the path, PROJECT_SLUG = FIRST_ARG.
- If multiple matches are found: list them and ask the user to disambiguate using
<client-slug> <project-slug>form. - If no match: stop and tell the user the project was not found.
- If FIRST_ARG matches the pattern
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 · 71 lines · 10 tokens per session scan A 15e7e9c69e05
use-client is a command published in the GitHub repository 10Legs/freelance-developer-harness (33 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,065 once invoked, about $0.0000 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 2026-10-02.
Other commands, from other repositories
fire-todos
Capture, list, and manage todos during work sessions.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.
attune
AI-powered developer workflows with Socratic discovery.
start
Start a session — load state files, flag staleness, and give a briefing on current priorities, deadlines, and blockers.
agent
Create and manage custom AI agents.
bulk
Batch API processing with 50% cost savings.