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 smixs/disruptor-skills --skill slicing-into-tracer-bulletsgit clone --depth 1 https://github.com/smixs/disruptor-skillsWrote 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/smixs/disruptor-skills/slicing-into-tracer-bullets)<a href="https://agentmods.dev/skills/smixs/disruptor-skills/slicing-into-tracer-bullets"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/slicing-into-tracer-bullets/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/smixs/disruptor-skills/slicing-into-tracer-bullets"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/slicing-into-tracer-bullets.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 | $0.00077 | $0.01142 |
| Opus 5 | $0.00039 | $0.00571 |
| Sonnet 5 | $0.00015 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
slicing-into-tracer-bullets 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 12d 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slicing into tracer bullets
Stage contract
- Stage: 4. Breakdown · Kind: method
- Inputs: the canonical spec (stage 2) + the module boundaries (stage 3).
- Outputs: an ordered list of vertical slices, each with acceptance criteria,
scope boundaries, and
Blocked by:links — one slice = one build-loop run. - Entry gate: the spec is build-ready and it is bigger than one slice. A single-slice job skips this stage — build it directly.
- Done when: every slice is end-to-end (touches all layers it needs), demoable/verifiable alone, and its dependencies are stated. No horizontal-only ("schema-only", "API-only") items remain.
- Next: two engines. Sequential (default): the
converging-and-polishingskill — run the build loop once per slice, each in its own fresh session seeded from the spec + that one slice. Fleet (gate G3F: parallelizable across independent nodes AND budget for a worker fleet): thedelivering-mvp-fleetskill — it builds its own board from the spec + slices. - Maintains: —
Why vertical, not horizontal
A tracer bullet is a thin slice that cuts through all the layers it touches — schema, backend, adapter, UI, tests — and delivers one small end-to-end behavior that you can actually run and see. It is the opposite of a horizontal layer ("build the whole DB schema", then "build the whole API"), which produces nothing demoable until the last layer lands and hides integration risk until the end.
Why it matters for an agent build: each vertical slice is small enough to build, review, and converge in one focused session without the context filling up. The integration seams — the places things actually break — get exercised on slice #1, not discovered at the end. And each slice merges independently.
What makes a good slice
- End-to-end. It reaches every layer its behavior needs. If a slice can't be demoed or verified without a future slice, it isn't a slice yet — it's a layer.
- Demoable / verifiable alone. There's a concrete way to see it work: a request that returns the right thing, a screen that renders, a test that passes.
- Small. Sized to one build-loop run. If it won't converge in one session, split it.
- Scoped. State what it explicitly does NOT cover (goes to a later slice), so the builder doesn't gold-plate.
- Behavioral, not procedural. Describe what the slice must do (interfaces, contracts, acceptance criteria) — not how to code it, and not by pointing at file paths/line numbers that will have drifted by the time it's built.
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.
- 12d ago First seen · 89 lines · 77 tokens per session scan A 3f0d7c7069ea
slicing-into-tracer-bullets is a skill published in the GitHub repository smixs/disruptor-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,142 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
setting-up-a-project
Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…