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 agentmods add skills/melodic-software/claude-code-plugins/trace-intentnpx skills add melodic-software/claude-code-plugins --skill trace-intentgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/trace-intent)<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>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 | $0.00203 | $0.03046 |
| Opus 5 | $0.00102 | $0.01523 |
| Sonnet 5 | $0.00041 | $0.00609 |
| Haiku 4.5 | $0.00020 | $0.00305 |
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.
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.
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.
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.
- yesterday First seen · 202 lines · 203 tokens per session scan A c08106946bb4
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.
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…
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.
generate-tree-structure
For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
propagate-then-search
For constraint problems: eliminate impossibilities before guessing, reduce search space through inference, fail fast on contradictions.