CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

jbaruch/herdr-policy

Herdr team coordination policy for AI coding agents

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

workflow-developer.mdskills/herdr-foreman/templates/

Implementation responsibility

Implement the admitted task in its provisioned writer worktree. Preserve the registered base, authorized paths, original task and cumulative correction number. Read the current blocking reports named by this attempt; settle only their in-scope blocking findings. Advisory-only feedback adds no repair work.

Run appropriate checks, inspect the actual diff and leave the writer clean with the intended changes committed on its feature branch. Supply actual implementation check evidence and the full current head. A complete built report enables independent verification; it grants neither acceptance nor release. Open no independent writer and perform no merge or publication.

Use built only when this attempt is complete. Use blocked for an unmet dependency, unavailable check, unsettled cause or changed scope/effect plan. Do not reset the task, invent a passing result or repair unrelated work.

skills

herdr-foreman

antigravity.example.json

bootstrap-repository.py

compose-briefs.sh

config.example.json

foreman-tier-check.py

foreman.sh

label-workspaces.sh

measurements.py

native-hook.sh

observer-view.py

policy-paths.py

prepare-briefs.py

provision-worktree.sh

prune-report-caches.py

resolve-gates.sh

resolve-policy-paths.sh

review-package.sh

roster.sh

round-preflight.sh

SKILL.md

start-judge-worker.sh

state-schema.md

sweep-worktrees.sh

verify-authority.sh

wait-report.sh

workflow-review.py

README.md

tile.json