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 KaydenClark/LLM_Workbench --skill tracer-bulletgit clone --depth 1 https://github.com/KaydenClark/LLM_WorkbenchWrote 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/kaydenclark/llm_workbench/tracer-bullet)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/tracer-bullet"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/tracer-bullet/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/kaydenclark/llm_workbench/tracer-bullet"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/tracer-bullet.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 | $0.00034 | $0.00758 |
| Opus 5 | $0.00017 | $0.00379 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
tracer-bullet 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracer Bullet
A tracer bullet is a lean but complete slice that pierces every horizontal layer of the stack at once — schema, service, interface, and test — for one narrow behavior. Because it crosses the whole stack, it is demoable on its own and returns end-to-end feedback immediately. A slice that touches one layer is a horizontal shard: it compiles but proves nothing, and integration risk stays hidden until the last shard lands. Fire tracer bullets, not shards into the dark.
Use this discipline when defining a spec's Vertical Implementation Slices,
when a proposed slice names only one layer, and before assigning a slice to an
Engineer.
When the capability belongs to a v3 project, read workbench/manifest.json
before assigning the slice so its durable SPEC.md and evidence paths use the
declared lanes.
1. Map the stack
Name the project's real horizontal layers from its own source, not a generic
template. Read the nearest AGENTS.md, RUNBOOK.md, and existing source to fix
the layer list a finished feature must cross. A web feature usually crosses
persistence → service → interface → automated test; a CLI crosses input parsing
→ core logic → output → test. The map is done when every layer this project's
capability must pierce is named for this project.
2. Cut the narrowest complete path
Pick the thinnest end-to-end behavior a user or caller can observe, and cut one slice that crosses every mapped layer for exactly that behavior. Hold the width to one behavior; take full depth through all layers. State each slice as an observable outcome ("a caller saves one record and reads it back"), never as a layer ("add the table").
A sound tracer bullet:
- Complete path — crosses every layer named in step 1.
- Demoable alone — its proof is a check Kayden can run in under a minute.
- One context — fits a single fresh context window; when it will not, cut a thinner behavior, not a horizontal shard.
- Real seam — verified at a public seam, the way
/tddand/implementdrive behavior, not at internal wiring.
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.
- today Changed · -1 lines 239f4ab54600
- 3d ago First seen · 73 lines · 34 tokens per session scan A 0b51dc200ab4
tracer-bullet is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 758 once invoked, about $0.0002 per session on Opus 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 2026-09-07.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.