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.
npx skills add bearded-illirian/trailmark --skill dev-auto-firstgit clone --depth 1 https://github.com/bearded-illirian/trailmarkWrote 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/skills/bearded-illirian/trailmark/dev-auto-first)<a href="https://agentmods.dev/skills/bearded-illirian/trailmark/dev-auto-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/dev-auto-first/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/skills/bearded-illirian/trailmark/dev-auto-first"><img src="https://agentmods.dev/badge/skills/bearded-illirian/trailmark/dev-auto-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 27 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 41 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 105 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 108 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 124 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 141 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 232 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 88 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 169 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00119 | $0.02356 |
| Opus 5.5 | $0.00048 | $0.00942 |
| Sonnet 5.5 | $0.00024 | $0.00471 |
| Haiku 4.5 | $0.00012 | $0.00236 |
Grade A, and why
dev-auto-first scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Real integration via 3 endpoints on `{ops_host}`. The skill lives in the agent, hits the API via `Bash + curl`. How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev-Auto-First Protocol
Autonomous orchestrator of the per-block cycle. Runs instead of manual approval at each step: flow-first → library-first → plan-first → execute.
Key principle: dev-auto-first does not wait for the user's "ok" — it reads the artifact itself, validates it against the rules, and on success continues the chain. On blockers — it escalates to a chat bot and waits for a reply.
How it differs from manual mode:
| Manual | dev-auto-first | |
|---|---|---|
| flow-first waits for "ok" | User writes "go" | Skill validates artifact → auto-approve |
| library-first waits for "ok" | User writes "go" | Skill validates table → auto-approve |
| plan-first asks for mode | User picks 1/2/3 | Skill answers "1 — Autopilot" |
| Blocker in a skill | User decides | Escalation to chat bot |
Important: dev-auto-first is a SKILL, not an agent. Works in the same context,
manages sub-skills via Skill() calls.
Input
Task context ({slug}, {log_dir}) plus a list of blocks with status open or pending in the tracking database.
Output
Per-block auto-approve log lines to chat, artifacts from each sub-skill (flow-first / library-first / plan-first / report / user-note), and a final summary table with block statuses + escalation counts.
Hands off to
— (terminal). Final task closure is a separate step (ship-first invoked manually or from a future auto-closer).
Step 0 — Check task context
Check: are {slug} and {log_dir} known in the current session?
If yes — continue to Step 0.5.
If no — list latest task folders under {tasks_root}/log/, request user selection, set {slug} and {log_dir}.
Cannot skip. Without {log_dir} sub-skill artifacts cannot be read.
Step 0.5 — Load the block list
sqlite3 {tasks_root}/routing.db \
"SELECT block_num, title, status FROM task_blocks
WHERE task_id='{slug}' AND status IN ('open','pending')
ORDER BY sort_order;"
Save as {pending_blocks}. If empty — output "No blocks with status open/pending" and finish.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed e4f06268709d
- 1mo ago First seen · 273 lines · 119 tokens per session scan A cb7031acbc26
dev-auto-first is a skill published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,356 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stub_distance_skill
a deterministic stub returned by the override engine in unit tests.
generated_skill_1775724185480
Parse XBRL financial documents and extract key taxonomy elements into structured JSON format.
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.