trace-intent

trace-intent is a skill for Claude Code, Codex from melodic-software/claude-code-plugins. It costs 203 tokens per session (3,046 once invoked), scanned A, original, MIT.

A tool for reconstructing the reasons behind past software decisions from evidence outside the code, such as reviews, tickets, design documents, and incident records.

In plain words
What is it for?
Use it to investigate the history and rationale of implementation choices, cite supporting evidence, and separate direct evidence from supported, inferred, speculative, or unknown conclusions.
Why use it?
Code shows what a system does, but usually not why it was built that way. This tool helps avoid treating guesses as established facts and clearly marks what could not be confirmed.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the discovery plugin — 5 skills, 3 agents 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/melodic-software/claude-code-plugins/trace-intent
Any agent
npx skills add melodic-software/claude-code-plugins --skill trace-intent
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code, Codex.

Or install discovery, the plugin that ships this one along with the rest of its 5 skills, 3 agents.

Wrote 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.

agentmods badge for trace-intent

README.md
[![agentmods](https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/trace-intent.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/trace-intent)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/trace-intent"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/trace-intent.svg" alt="Measured on agentmods" height="20"></a>
Per session 203 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,046 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 $0.00203 $0.03046
Opus 5 $0.00102 $0.01523
Sonnet 5 $0.00041 $0.00609
Haiku 4.5 $0.00020 $0.00305

Measured yesterday against content hash c08106946bb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trace-intent 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 yesterday.

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/discovery/skills/trace-intent/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-computed context

Current branch: !git branch --show-current 2>/dev/null || echo "unknown" Project root: !git rev-parse --show-toplevel 2>/dev/null || echo "unknown"

Purpose

Code records what a system does. It rarely records why anyone chose it. That lives in review threads, tickets, design documents, and incident timelines. Records that are partial, contradictory, and sometimes gone. This skill reconstructs intent from those records and is honest about the parts it could not recover.

Third axis of this plugin. /discovery:explore answers what IS, /discovery:research answers what SHOULD BE, and this answers what WAS, and why. The failure it exists to prevent is a confident story built from thin evidence: a plausible narrative about a decision is worse than an admission of ignorance, because it is acted upon.

Routing. Dispatch by default

From the main conversation, this skill dispatches the discovery:intent-tracer subagent. Intent archaeology reads a lot of other people's writing: review threads, ticket histories, design documents. Keeping that out of the orchestrator's context window is the point. The agent investigates each resolvable category, writes the artifact set, and returns a file pointer plus a verification request, not the transcript. The parent resolves the pre-dispatch envelope first: six fields (target on the Topic: line, reason, memory-slice path, memory root, budget, capability flags), written into the dispatch prompt as the labelled template in the parent contract, and owns the post-dispatch boundary after: re-surfacing open_questions, dispatching the sibling verifier for tier assignment, and writing that verdict back into the index.

Run inline instead for tight turn-by-turn iteration, for cost, or when the invoking context is already a subagent, and inline runs the identical discipline; the escape hatch relaxes nothing below. An un-runnable gate is not one of the three reasons: probe --help on the artifact checker before dispatching, and a denied or errored probe halts rather than routing you inline. All three reasons in full, and the halt rule: context/dispatch.md.

Read the full file on GitHub · 202 lines

Files

What ships with it

5 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. yesterday First seen · 202 lines · 203 tokens per session scan A c08106946bb4

Subscribe to this mod's changes

trace-intent is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 203 tokens to every session and 3,046 once invoked, about $0.0010 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 2026-09-03.

Related

Other skills, from other repositories

parallel-orchestrator

Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…

jimmc414/claude-code-plugin-marketplace · 78 tokens

parallel-worker

Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.

jimmc414/claude-code-plugin-marketplace · 59 tokens

generate-tree-structure

For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.

jimmc414/claude-code-plugin-marketplace · 30 tokens

optimize-local-search

For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).

jimmc414/claude-code-plugin-marketplace · 31 tokens

pass-function-as-arg

For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.

jimmc414/claude-code-plugin-marketplace · 27 tokens

propagate-then-search

For constraint problems: eliminate impossibilities before guessing, reduce search space through inference, fail fast on contradictions.

jimmc414/claude-code-plugin-marketplace · 27 tokens