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/scrutinize-dont-coast)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/scrutinize-dont-coast"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/scrutinize-dont-coast/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/scrutinize-dont-coast"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/scrutinize-dont-coast.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 | $0.00107 | $0.01776 |
| Opus 5.5 | $0.00043 | $0.00710 |
| Sonnet 5.5 | $0.00021 | $0.00355 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade A, and why
scrutinize-dont-coast 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrutinize, don't coast
A drift corrector for adversarial self-scrutiny. 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 adversarial self-scrutiny,
and the three declared deltas this corrector makes to the shared loop.
The discipline this re-anchors
This corrector re-anchors a meta discipline: adversarial self-scrutiny of your own recent output. The lens is not "does this conform to discipline X" but "is this actually right, and would it survive a hostile second look."
Resolve the source of truth per the method doc's ladder: if the consuming project
states a self-scrutiny / verify-before-acting discipline in its own CLAUDE.md or
.claude/rules/, re-anchor THAT. Otherwise re-anchor this portable baseline:
- Confidence is not correctness. Output that flows smoothly and reads as finished has not thereby been tested. Treat "this looks done" as the cue to scrutinize, not the verdict.
- Attack the work, don't defend it. The pass looks actively for what is wrong (a wrong assumption, an unstated leap, a case not handled, a claim not backed, a requirement quietly dropped) rather than re-reading for reassurance.
- The producing context is the weakest critic. The reasoning that made a mistake plausible is still active, so a hostile look must come from outside it (see the fresh-context rule below).
- A clean pass is a real outcome. Scrutiny that finds the work sound reports clean. The duty is to look hard, not to manufacture a fault.
Three deltas to the shared loop
Declared here per the method doc's "Declared step deltas" allowance:
- Stop first. An inserted step between the loop's step 1 and step 2: re-anchoring happens on skill load as always, then the current trajectory halts before the audit runs. Do not push the in-flight action one step further before the re-examination has run: the trigger is "you are moving too fast on this."
- Remediate with the user, not autonomously. The shared loop's step 3 (correct forward) becomes collaborative: surface the adversarial findings and work the fixes with the user rather than barrelling ahead into an autonomous rewrite. The user just hit the brakes, so they stay in the loop on what changes. Purely mechanical, unambiguous corrections (a typo the pass surfaced) are still fixed directly; anything carrying a judgment call is proposed and worked jointly.
- The step 2 self-audit runs in a fresh-context subagent, not in the producing thread (next section).
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 · -17 lines 2020b33f7e06
- 7d ago Changed · +2 lines 28f619d198f2
- 22d ago Changed · -11 tokens per session eaf1bf74f0bd
- 27d ago Changed 9f642cf2f6a5
- 1mo ago Changed · -2 tokens per session bceeb99a9b4f
- 1mo ago Changed · +6 lines 75be8b28bc84
- 1mo ago First seen · 144 lines · 120 tokens per session scan A 5a8ed1b57852
scrutinize-dont-coast is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 1,776 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.
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.
handle-edge-cases
For boundary conditions: empty collections, zero values, recursive base cases, null checks, prevent crashes at edges.
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…