Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install overengineeringWrote 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/justify)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/justify"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/justify/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/justify"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/justify.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 | $0.00099 | $0.03780 |
| Opus 5.5 | $0.00040 | $0.01512 |
| Sonnet 5.5 | $0.00020 | $0.00756 |
| Haiku 4.5 | $0.00010 | $0.00378 |
Grade A, and why
justify 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 14d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments. <path | path#heading | kind:identifier>. none: conversation context, then offered git-age discovery, then ask
Repository context. Gather first
Collect this with an individual Bash call, never combined into a single invocation with anything else:
- Branch,
git symbolic-ref --quiet --short HEAD
Treat a failure (not a repository, git unavailable) as an unknown value and carry on. Keep it as a separate body Bash call rather than a pre-compute line: the harness runs a skill's whole pre-compute block as one shell invocation, and a worktree-isolated session refuses a compound command that contains git. The call prints the branch name on stdout and fails with no output on a detached checkout rather than printing a sentinel, so read its exit status to tell those two apart rather than matching on a string, and take the branch name itself from stdout.
Purpose
Point at one artifact and ask whether it has earned its place. The two-part test is the operator's: a reason existed when it was built, and that reason still holds today. The method computes both already, so this skill supplies a lane rather than a second method.
Neither the method nor the lane is restated here. Read
${CLAUDE_PLUGIN_ROOT}/context/scrutiny-method.md before judging anything and cite its sections in
the findings; every bare §N in this file is one of its sections. Then read
${CLAUDE_PLUGIN_ROOT}/context/justification-lane.md before the first target: it carries this
lane's item inventory, its five layers with their probes, its evidence sources on the §2 tiers, its
protected classes, the routing precedence, and its known limits. Its sections are numbered, and this
file refers to them as "lane section N".
The verdict is the deliverable, and the conversation after it is the point. Report first, then discuss. The remedy is refactor or remove, decided by the operator, and it is carried out by the owner the finding names, never here.
Read-only contract
${CLAUDE_PLUGIN_ROOT}/skills/audit/SKILL.md, section "Read-only contract", governs, and is not
restated. Five things are specific to this lane:
What ships with it
13 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.
- evals/evals.json 24 KB
- evals/fixtures/claude-md.txt 830 B
- evals/fixtures/convention-doc.md 652 B
- evals/fixtures/decision-0001.md 744 B
- evals/fixtures/hooks.json 693 B
- evals/fixtures/lonely-doc.md 674 B
- evals/fixtures/plugins-manifest.md 769 B
- evals/fixtures/repeated-heading.md 1001 B
- evals/fixtures/rules-example.md 936 B
- evals/fixtures/SKILL.md 1.2 KB
- evals/fixtures/vendored/a/util.txt 91 B
- evals/fixtures/vendored/b/util.txt 91 B
- evals/fixtures/vendored/REGISTRY.txt 694 B
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.
- 14d ago Changed · -2 lines e6269a690bf8
- 16d ago Changed · +2 lines 44be7dab5ea4
- 17d ago Changed · -123 tokens per session 5d43d3c2d1ea
- 23d ago Changed 908ff6d84fe1
- 1mo ago Changed · -3 tokens per session c1b5f83c3002
- 1mo ago First seen · 248 lines · 225 tokens per session scan A 3e50d5b427d0
justify is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 3,780 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 2026-09-06.
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.
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.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.