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 melodic-software/claude-code-plugins --skill targetgit 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/target)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/target"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/target/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/melodic-software/claude-code-plugins/target"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/target.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 | $0.00102 | $0.01757 |
| Opus 5.5 | $0.00041 | $0.00703 |
| Sonnet 5.5 | $0.00020 | $0.00351 |
| Haiku 4.5 | $0.00010 | $0.00176 |
Grade A, and why
target 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 23d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments. [<path|component|'session'|'telemetry'>]. e.g. /performance:target plugins/disk-hygiene/hooks
Purpose
Answers "what should we optimize, and how much do we actually know about it?"
The failure this prevents is picking a target because its mechanism sounds expensive. Take a diagnosis of WDAC code-integrity enforcement as the cause of slow process spawns: the mechanism is real and the policy may genuinely be enabled, and it is still the wrong answer when the data says otherwise. A spread of min 180.5 ms / median 1107.7 ms / max 2841.3 ms across identical no-op spawns is a contention signature, because a fixed policy check cannot produce a 15x spread. The bimodality is the diagnosis; the plausible mechanism is a distraction.
So this skill ranks by evidence, and says so when there is none.
Inputs it accepts
| Source | What to do |
|---|---|
| The current session's own pain | Name the operation that felt slow and what was observed. A screenshot or recording counts. Anecdote is a valid candidate source and an invalid ranking basis. |
| A named path or component | Enumerate the layers it spans before choosing one (see "Measure the layers first"). |
| A telemetry store | /claude-ops:observability for Claude Code's own; otherwise the project's. Prefer it over every other source, after checking its accuracy and coverage. |
| Open-ended "what is slow here" | Widest scope, weakest evidence. Expect the output to be "instrument this first". |
Evidence tiers
Rank every candidate into exactly one. A lower tier never outranks a higher one, regardless of how compelling the mechanism sounds.
| Tier | Means | Example |
|---|---|---|
| E1, attributed measurement | A measurement that isolates this component's cost from its neighbors' | A spawn census showing this hook costs 4 of the 7 spawns per tool call |
| E2, aggregate measurement | A real measurement that includes this component but does not isolate it | "The whole pre-tool path takes 1.2 s" |
| E3, structural inference | No measurement; a documented cost model predicts expense | "This is a 125-line shell wrapper that runs per tool call" |
| E4, suspicion | A plausible mechanism and nothing else | "WDAC is probably slowing spawns" |
What ships with it
1 file 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.
- 23d ago Changed · +2 lines a2d06bc431b6
- 24d ago Changed · +6 lines · -104 tokens per session b4363bca0b28
- 28d ago Changed · +11 lines 1c855a9452cf
- 1mo ago Changed 62c10e4d7913
- 1mo ago Changed · +2 tokens per session b85c6d508008
- 1mo ago First seen · 111 lines · 204 tokens per session scan A 55de9ff7f228
target is a skill published in the GitHub repository melodic-software/claude-code-plugins (27 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 1,757 once invoked, about $0.0004 per session on Opus 5.5. 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
adversarial-analysis
Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.
benchmark-before-optimize
For performance work: measure before changing, profile to find bottlenecks, compare before and after.
handle-edge-cases
For boundary conditions: empty collections, zero values, recursive base cases, null checks, prevent crashes at edges.
validate-before-process
For input validation: check format and constraints before processing, fail fast with clear errors, defensive parsing.
display-grid-state
For 2D debugging: visualize grid/board state, show puzzle progress, make algorithm behavior visible.
claim-check
Claim checker that audits a coding agent's statements that tests pass or a build is clean against its own session transcripts: whether a matching run happened before the claim, whether it passed, and whether code changed after it. Use when the user asks whether the agent really ran the tests, how often it said tests…