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 disciplineWrote 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/point-dont-copy)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/point-dont-copy"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/point-dont-copy/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/point-dont-copy"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/point-dont-copy.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 | $0.00094 | $0.01506 |
| Opus 5.5 | $0.00038 | $0.00602 |
| Sonnet 5.5 | $0.00019 | $0.00301 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade A, and why
point-dont-copy 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments. [target]. e.g., /discipline:point-dont-copy the new setup guide, or empty to audit the work in flight
Point, don't copy
A drift corrector for pointer-over-copy discipline. The shared method
(re-anchor, audit the work in flight, correct forward, report) lives in
${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md.
Read it; this file adds only what is specific to duplication discipline.
The discipline this re-anchors
Point at the living source; do not copy what it owns. Convention docs already own this doctrine: re-anchor THEM, do not restate them. Resolve the source of truth per the method doc's ladder:
- Facts you own (in-repo). Your organization's reference-don't-duplicate convention. Every fact has one source of truth; consumers cite it by a stable anchor rather than restate it; literal versus semantic duplication; the describe / use / expose roles a file plays toward a fact.
- Facts an upstream owns (external). Your organization's documentation-and-citations convention. Cite the upstream and fetch it at read time; do not recap upstream-owned catalogs, schemas, flag inventories, or defaults into tracked files; place the citation at the sentence that defers to it; a stored external value needs a recheck trigger.
Read those where they live. When a consuming project declares none of them, re-anchor the portable baseline: provide a link or citation to the living source and never restate the facts it owns: a reworded paraphrase drifts exactly as a verbatim copy does, because both are a second copy that goes stale when the source moves.
This skill's own pins. Beyond what the conventions state
- Threshold two. Whatever count the resolved convention's smell signals fire at, this skill pins the trigger at two: the second copy is already duplication to resolve by pointing, not something to tolerate until a third appears. Weigh a genuine case for local divergence on its merits, but the default at two copies is to consolidate to one source and point at it.
- Point at public contracts, not internals. Reference the stable public contract (a tool's invocation surface, the command and its arguments), never the internal script or file names behind it, which break every citation the moment they move.
- No capability enumeration. Phrase your OWN duties open-ended, not just upstream-owned inventories. A closed list of what something can do goes stale as the surface evolves; name current mechanisms only as clearly-marked examples. "mechanisms such as X and Y (examples, not a fixed list)", never as the definition.
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.
- 5d ago Changed · -9 lines · +1 tokens per session 0f7c3bbac8ea
- 20d ago Changed · +2 lines 51cc917ec1fe
- 1mo ago Changed · -2 lines fef98838ef4c
- 1mo ago First seen · 133 lines · 93 tokens per session scan A 9a1ad9d4d029
point-dont-copy is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,506 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
refactor-decompose-function
For long functions: break into smaller pieces, extract helper functions, reduce nesting, improve testability and readability.
pr-analyzing
Use this skill when the user asks to analyze a specific GitHub pull request, review a PR's architectural impact, assess what changed in a PR and why it matters, or research the code relationships affected by a PR — example triggers like "analyze PR.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
find-shortest-path
For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.
visual-design-system
World-class visual design system standards — OKLCH color science, fluid typography, elevation hierarchy, branded asymmetric corners, and dark mode implementation.
css-coding-standards
CSS coding standards for systemprompt.io — one --sp- token system in OKLCH with color-mix derivation, BEM naming, one component per file, CSS-first behaviour, forbidden constructs, comment rules, and file limits. Canonical source of truth for all CSS. Load before writing or reviewing any stylesheet.