BD Herdr
Operates herdr, the terminal workspace manager for coding agents, through its CLI and socket API, explains and edits the local herdr setup (config.toml key mirror, shell wrapper, terminal passthrough maps, sidebar naming, agent-state integrations), and checks the install against upstream. USE WHEN herdr, herder, herd, herdr command, herdr pane, herdr tab, herdr workspace, herdr worktree, start an agent in a pane, prompt the agent in the other pane, read that pane, what are my other agents doing, herdr config, herdr keybinding, herdr sidebar, herdr integration, herdr docs, update herdr, is herdr up to date, herdr remote, herdr machine. NOT FOR in-harness subagents (Agent or Workflow), the Helm terminal itself outside herdr (Helm docs), the Hermes sidecar (Hermes).
Operates herdr, the terminal workspace manager for coding agents, through its CLI and socket API, explains and edits the local herdr setup (config.toml key…
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-useSKILL.md:57Credential used in a network call (verify the destination is the intended service)curl -fsSL "<config reference URL from the index>" | jq --arg key 'ui.sidebar_width' '.sections[].keys[] | select(.key == $key)'
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "evals"
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1860 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 773: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.