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/dorukanc/harness-councilWrote 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/dorukanc/harness-council/init)<a href="https://agentmods.dev/commands/dorukanc/harness-council/init"><img src="https://agentmods.dev/badge/commands/dorukanc/harness-council/init/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/dorukanc/harness-council/init"><img src="https://agentmods.dev/badge/commands/dorukanc/harness-council/init.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 | $0.00024 | $0.00344 |
| Opus 5.5 | $0.00010 | $0.00138 |
| Sonnet 5.5 | $0.00005 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
init 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 2mo 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.
What it actually says
Set up Harness Council overrides for the current project.
First make it clear this is optional: council already works in every project
(user-scope MCP + the council-runtime skill). init only exists to pin
project-specific routing.
Run:
council init
This writes two files, both idempotent — re-running updates the managed block in place and never touches the user's own content:
.harness-council.toml— a fully commented template showing what this project resolves to today. Commented values keep inheriting~/.harness-council/config.toml; uncommenting pins them to this repo.CLAUDE.md— a<!-- harness-council:start -->block describing council and the current role table.
Useful flags: --file AGENTS.md (when another harness orchestrates this repo),
--force (overwrite an existing toml), --no-toml / --no-doc.
Extra context from the user: $ARGUMENTS
If they described project-specific routing rules (e.g. "always explore first here",
"code should go to Claude in this repo"), then after running init:
- Uncomment and edit the matching keys in
.harness-council.toml. - Replace the guidance placeholder comment inside the CLAUDE.md block with those rules in plain prose.
- Re-read the files back to the user and summarize what changed.
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.
- 2mo ago First seen · 38 lines · 24 tokens per session scan A 734566451ac4
init is a command published in the GitHub repository dorukanc/harness-council (2 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 344 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 2026-08-31.
Other commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
security
Scan a SQL string, .sql file, or SQL-building source file for injection risks with GoSQLX.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
amp-register
Register your agent with an external AMP provider for cross-provider messaging.
speckit.spec-stats.open
On-demand view of everything not complete: what stage each is stuck at, what the immediate next artifact/command is, oldest-untouched first, stale warnings past staleafterdays.