tracer

A code-tracing method for following execution paths, dependencies, or data flow through an unfamiliar codebase.

In plain words
What is it for?
It is for mapping call chains, dependencies, data transformations, side effects, and debugging paths from a known entry point.
Why use it?
It helps an agent identify which files and functions are involved in a behavior without reading unrelated parts of the project.

Skill for Claude CodeCodex

Part of the flow plugin — 21 skills, 18 commands, 7 agents, 1 hook shipped together

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/cofin/flow/tracer
Any agent
npx skills add cofin/flow --skill tracer
Clone the repo
git clone --depth 1 https://github.com/cofin/flow

Made for: Claude Code, Codex.

Or install flow, the plugin that ships this one along with the rest of its 21 skills, 18 commands, 7 agents, 1 hook.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 303 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 $0.00038 $0.00303
Opus 5 $0.00019 $0.00151
Sonnet 5 $0.00008 $0.00061
Haiku 4.5 $0.00004 $0.00030

Measured 3d ago against content hash d992803ef11f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tracer 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 3d 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.

plugins/flow/skills/tracer/SKILL.md · 59 lines

What it actually says

Tracer

Trace code from a known entry point, following evidence-linked edges until the question is answered.

Workflow

  1. Load the tracing strategy and mode-selection reference below.
  2. Select execution, dependency, or data mode from the question.
  3. Follow and record relevant edges, then synthesize the resulting map at the documented stop condition.

Guardrails

Do not open unrelated files, trace every branch indiscriminately, or cross a third-party boundary unless the question requires it.

Output

Return the selected mode, an ordered path or dependency/data map with file and symbol locations, transformations and side effects, and a concise answer to the original question.

Validation

Confirm every inspected node follows from a recorded edge and the trace stops only after the question or critical path is resolved.

Example

Map an HTTP handler through its service and repository to the database call, annotating the data transformation at each node.

References

Files

What ships with it

3 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.

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. 3d ago First seen · 59 lines · 38 tokens per session scan A d992803ef11f

Subscribe to this mod's changes

tracer is a skill published in the GitHub repository cofin/flow (15 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 303 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 2026-08-30.