tracer-bullets

A method for planning features as small vertical slices that pass through every needed layer, such as the command line, parsing, database, tests, and documentation. A vertical slice delivers one working behavior across the system.

In plain words
What is it for?
Use it to plan new file-format support, database schema changes, command-line flags, and other features that span multiple parts of the codebase.
Why use it?
It reduces the risk of building disconnected layers that do not work together or agree about the feature.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stainless-code/codemap/tracer-bullets
Any agent
npx skills add stainless-code/codemap --skill tracer-bullets
Clone the repo
git clone --depth 1 https://github.com/stainless-code/codemap

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00710
Opus 5 $0.00026 $0.00355
Sonnet 5 $0.00011 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 2d ago against content hash 23d99d6ca49d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.agents/skills/tracer-bullets/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tracer bullets — codemap feature layers and examples

Always-on rule: .agents/rules/tracer-bullets.md (the 5 rules + lite-harden). This skill carries the codemap layer map and worked examples.

Feature layers in this project

A typical vertical slice for codemap touches these layers top-to-bottom:

  1. CLI / orchestrationsrc/cli/ (bootstrap.ts, main.ts, lazy cmd-* chunks; entry src/index.ts)
  2. Workers / parsingsrc/parse-worker.ts / parse-worker-node.ts, parse-worker-core.ts, src/parser.ts, src/css-parser.ts, src/adapters/
  3. Persistencesrc/db.ts (schema, inserts, SCHEMA_VERSION)
  4. Config / runtimesrc/config.ts, src/runtime.ts, resolver
  5. Testssrc/*.test.ts
  6. Docsdocs/*.md when behavior is user-visible

Example 1: Support a new source extension

Bad — building in layers:

  • Update every glob, parser, and docs in one giant change
  • Hope CI and the index agree

Good — tracer bullet:

  1. constants + adapterLANG_MAP + builtin adapter extensions + extractFileData — commit, bun run check, small test parsing a one-line file
  2. Resolverresolver extensions if needed — commit, validate
  3. Docsdocs/architecture.md table row — commit, validate

Example 2: Add a new SQLite column or table

Bad — schema + all call sites + benchmarks in one unreviewable diff.

Good — tracer bullet:

  1. Schema + insert pathdb.ts + one write path exercised by a test or CLI run — commit, validate
  2. Readers / query UX — expose in query or docs — commit, validate
  3. Benchmark / fixtures — if numbers matter — separate commit

Example 3: New CLI flag

Bad — flag parsing, help text, config, and tests all speculative.

Good — tracer bullet:

  1. Parse flag + minimal behavior — e.g. --dry-run that only logs — commit, test
  2. Wire to real work — connect to indexer — commit, validate
  3. Document — README / docs/architecture.md — commit

Read the full file on GitHub · 60 lines

Changes

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.

  1. 2d ago First seen · 60 lines · 53 tokens per session scan A 23d99d6ca49d

Subscribe to this mod's changes

tracer-bullets is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed 7d ago), licensed MIT. It adds 53 tokens to every session and 710 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories