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/recheck-against-upstream)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/recheck-against-upstream"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/recheck-against-upstream/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/recheck-against-upstream"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/recheck-against-upstream.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 | $0.00130 | $0.01757 |
| Opus 5.5 | $0.00052 | $0.00703 |
| Sonnet 5.5 | $0.00026 | $0.00351 |
| Haiku 4.5 | $0.00013 | $0.00176 |
Grade A, and why
recheck-against-upstream 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recheck against upstream
A drift corrector for the discipline that existing state does not vouch for
itself. 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 upstream-conformance
discipline.
The discipline this re-anchors
Existing state, a config file, a code path, a runbook, an infra
definition, is evidence of what is, never proof that it matches the
upstream it depends on. Resolve the source of truth per the method doc's
ladder: if the consuming project states an upstream-conformance rule in its
own CLAUDE.md / .claude/rules/, re-anchor THAT. Otherwise re-anchor this
portable baseline:
- Present state is not self-justifying. "It's already configured this way" and "the code does X" describe the state; neither shows it still matches upstream. Conformance is a claim to verify, not to assume.
- Compare against the CURRENT official upstream, fetched now. Re-read
the vendor's live documentation for the surface in play this session, never training-data recall of it, never a stale in-repo summary of it.
Read each docs page through the shared docs lookup, not a WebFetch
summary: the procedure is
${CLAUDE_PLUGIN_ROOT}/reference/docs-lookup-procedure.md. Read it before the first fetch and follow it, with<scripts>=${CLAUDE_PLUGIN_ROOT}/scripts(fetch-docs.sh --cache) and<session>=${CLAUDE_SESSION_ID}. Report each page's age. A read that settles a verdict uses raw bytes (the procedure's step 6). A source that is not a docs page, such as a changelog repository or GitHub release notes, keeps its existing route. - Resolve the applicable upstream version first. When the repo pins a supported major/minor, compare against the docs for THAT version. The latest docs can legitimately prescribe APIs and defaults the pin does not have. Divergence between the pinned line and latest is its own finding (upgrade candidate or deliberate hold), never a false gap against the pin.
- Unverified conformance is not "clean". A surface you did not compare is unaudited, not passing. Report what was compared and what was skipped; do not launder the unchecked into a green result.
What ships with it
2 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.
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 · -10 lines 62bc091bbc0f
- 8d ago Changed · +27 lines · +24 tokens per session 116a7713b044
- 12d ago Changed · +9 lines 980ac7f1d894
- 22d ago Changed · -8 tokens per session 806ebede1a79
- 1mo ago First seen · 105 lines · 114 tokens per session scan A 7cde1be8b7bd
recheck-against-upstream is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 1,757 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.