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/reason-dont-recite)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/reason-dont-recite"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/reason-dont-recite/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/reason-dont-recite"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/reason-dont-recite.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 | $0.00113 | $0.01114 |
| Opus 5.5 | $0.00045 | $0.00446 |
| Sonnet 5.5 | $0.00023 | $0.00223 |
| Haiku 4.5 | $0.00011 | $0.00111 |
Grade A, and why
reason-dont-recite 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reason, don't recite
A drift corrector for incumbency 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 interrogating inherited
content.
The discipline this re-anchors
Inherited content, a repo's docs, conventions, structure, processes, is
evidence of what is, never a self-justifying argument for what should
be. Resolve the source of truth per the method doc's ladder: if the
consuming project states an incumbency / first-principles rule in its own
CLAUDE.md / .claude/rules/, re-anchor THAT. Otherwise re-anchor this
portable baseline:
- Precedent describes, it does not justify. Existing structure, coupling, "how it's always been done", and "I don't know why, it just is" describe the current state; none is an argument that the state is correct.
- Descriptive-only support earns a challenge. A rule, boundary, or process whose only backing is that it already exists gets re-derived from first principles. State the actual purpose, then test whether the incumbent form serves it, not obeyed on sight.
- A live rationale is different from inertia. A convention someone can justify on its merits is followed; one coasting on incumbency is interrogated. Separate the two before acting.
- Absence today is not out of scope. Do not dismiss a concern merely because the thing it depends on does not exist yet; judge it on its merits.
This is a distinct axis from /discipline:do-your-research. That skill
acquires external evidence you LACK; this one questions internal evidence
you INHERITED and took on faith. The audit may find every inherited choice
is well justified.
Audit. What to look for
Name concrete, located findings (per the method doc's step 2, self-audit):
- a decision justified only by precedent. "that's how this repo does it", "the existing code does X, so match it", with no rationale stated;
- a convention followed while nobody can say what it is for;
- inherited structure treated as a hard constraint when it is only the current state;
- a "we can't, it's always been this way" that was never re-derived;
- a concern waved off solely because its dependency does not exist yet.
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 · -11 lines · +2 tokens per session 9824d9cc3b1e
- 22d ago Changed · -72 tokens per session 06b3513689f1
- 1mo ago Changed ed037c2624f6
- 1mo ago First seen · 103 lines · 183 tokens per session scan A 7d19e7948054
reason-dont-recite is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 1,114 once invoked, about $0.0005 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.
return-none-for-failure
For graceful failure: return None or False instead of exceptions, let caller decide how to handle failure.