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/mind-your-maxims)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/mind-your-maxims"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/mind-your-maxims/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/mind-your-maxims"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/mind-your-maxims.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 | $0.00105 | $0.01167 |
| Opus 5.5 | $0.00042 | $0.00467 |
| Sonnet 5.5 | $0.00021 | $0.00233 |
| Haiku 4.5 | $0.00011 | $0.00117 |
Grade A, and why
mind-your-maxims 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mind your maxims
A drift corrector for cooperative-communication 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 communication discipline.
The discipline this re-anchors
Cooperative communication: give the reader what they need. No less, no
more. Relevantly, clearly, and with your uncertainty and limits disclosed.
The maxims are owned by their primary sources; point at them, do not
restate them (this skill dogfoods /discipline:point-dont-copy: a paraphrase
here would be a second copy that drifts):
- Grice's Cooperative Principle and its four maxims. Quantity, Quality, Relation, Manner. In Grice, "Logic and Conversation" and Cooperative principle.
- The AI-augmented maxims for human-AI dialogue. Transparency and Benevolence. In Miehling et al., "Language Models in Dialogue: Conversational Maxims for Human-AI Interactions" (arXiv:2403.15115).
Resolve the source of truth per the method doc's ladder: if the consuming
project declares a communication or writing-quality convention in its own
CLAUDE.md / .claude/rules/, re-anchor THAT as well and audit against it.
The rubric this skill audits
The four axes this corrector owns, mapped onto the pointed-to maxims:
- Quantity, both directions. Under-informing is a finding: an asked-for detail, a load-bearing caveat, or a necessary step omitted. Over-informing is a finding too: padding, restatement, and detail the reader did not need.
- Relation. Answer the question actually asked. An adjacent answer to a question the reader did not ask, a tangent, or a buried lede (the answer present but hidden below setup) fails relevance even when technically correct.
- Manner. Unambiguous references (no pronoun or "it" the reader must resolve), ordered structure, and plain clarity over cleverness or needless jargon.
- Transparency. Disclose the boundaries: flag genuine uncertainty rather than asserting through it, and state the edges of your knowledge or capability rather than letting the reader assume completeness.
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 · -19 lines 44137c8432a9
- 20d ago Changed 66ec7bdd73f2
- 22d ago Changed · -10 tokens per session 85ab168fa2ac
- 1mo ago Changed · -1 lines 908957c47381
- 1mo ago First seen · 113 lines · 115 tokens per session scan A ac370cb8d9b7
mind-your-maxims is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 1,167 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
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).
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.
validate-before-process
For input validation: check format and constraints before processing, fail fast with clear errors, defensive parsing.