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/pm)<a href="https://agentmods.dev/commands/10legs/freelance-developer-harness/pm"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/pm/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/pm"><img src="https://agentmods.dev/badge/commands/10legs/freelance-developer-harness/pm.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 | $0.00013 | $0.00729 |
| Opus 5.5 | $0.00005 | $0.00292 |
| Sonnet 5.5 | $0.00003 | $0.00146 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
pm 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session-scoped PM lock
The PM command is session-scoped.
PM mode state is stored in .claude/sessions/<SESSION_ID>.pm-mode (contains "on" or "off").
Special subcommands — handle these directly without spawning an agent:
If $ARGUMENTS is "on":
- The SESSION_ID is injected into the system prompt as
SESSION_ID = <value>. Read it from there; if not present, use "default". - Run
mkdir -p .claude/sessions && echo "on" > ".claude/sessions/<SESSION_ID>.pm-mode"via Bash. - Confirm: "PM mode enabled. Every prompt will now be routed through the PM."
- Stop here.
If $ARGUMENTS is "off":
- 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>.pm-mode" && echo "off"via Bash. - Confirm: "PM mode disabled."
- Stop here.
If $ARGUMENTS is "status" or "list":
- The SESSION_ID is injected into the system prompt as
SESSION_ID = <value>. Read it from there; if not present, use "default". - Run
ls .claude/sessions/*.pm-mode 2>/dev/null || echo "(none)"via Bash to find all sessions with PM mode enabled. - For each
.pm-modefile found, print the session ID (filename without.pm-mode) and whether mode is on/off. - Print current session PM mode status: ON or OFF.
- Stop here.
Otherwise — invoke the PM agent
Use the Agent tool to spawn the product-manager subagent with the following task:
Task: $ARGUMENTS
Instructions for the PM agent:
You are being invoked to lead and orchestrate the following work: $ARGUMENTS
Execute the full automated workflow:
-
Assess the request — Is this intake (new project), a sprint (ongoing work), or a targeted delegation (specific epic/feature)?
-
Load context — Read the active client lock at
.claude/sessions/<SESSION_ID>.clientif present (contents:<client>or<client>/<project>). Use it to locate the correct workspace underclients/<client>/projects/<project>/. If no lock is set, ask once and run/use-clientbefore proceeding — without a lock the client boundary guard is inactive.
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 · 59 lines · 13 tokens per session scan A 98fd40b0cd9a
pm is a command published in the GitHub repository 10Legs/freelance-developer-harness (33 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 729 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 2026-10-02.
Other commands, from other repositories
dashboard
Starts the live web dashboard for the current fellowship — quest/scout progress, gate approvals, and event history — in the background, and prints the URL.
mega-status
Show detailed status of mega-plan execution including feature progress and story completion. Usage: /plan-cascade:mega-status.
hybrid-status
Show execution status of all stories in the PRD. Displays batch progress, individual story states, completion percentage, and recent activity logs.
issues-setup
Set up issue tracker integration (Linear, Jira, or GitHub Issues) via MCP.
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.
hybrid-complete
Complete Hybrid Ralph task in worktree, verify all stories complete, commit code changes (excluding planning files), merge to target branch, and cleanup worktree directory. Can be run from any directory.