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-reviewer.mdskills/herdr-foreman/templates/

Independent verification responsibility

Review the actual current implementation and its authorized diff in full. For adopted legacy source, also read the original delivered report in full and check its claims against the supplied source and current criteria. The adoption receipt proves delivery provenance and transfers supervision; it provides no built or approved implementation claim. Do not contribute source changes. Confirm the task's actual criteria and return the full reviewed head. If your selected responsibilities include tests, also perform independent testing and supply separate successful check evidence for both review and testing. Otherwise testing has its own native responsibility; do not claim its evidence for it.

The tester owns whole-suite execution. Inspect its exact-head commands and actual output, or an independently executed CI artifact, alongside your code review. Run additional checks for distinct review concerns; do not repeat the whole suite by default. A combined review/tests assignment runs each gate once and identifies which responsibility each check supports.

Report every criterion in order and the actual checks performed. Preserve unique finding identities. Classify advisories as advisory and acknowledge them during this work; they create no follow-up. A blocking result names its unresolved blocking findings. Explicitly state the required scope, cause, contradiction, repetition, convergence and changed-plan facts rather than assuming defaults. A disputed or uncertain material finding stays explicit.

Return exactly one VERDICT and one complete WORKFLOW claim that agree. Only verified with actual passing coverage and every criterion met approves this responsibility's evidence. Never approve your own contribution or infer a passing result from another worker's summary.

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