Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/melodic-software/claude-code-plugins/do-your-researchnpx skills add melodic-software/claude-code-plugins --skill do-your-researchgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/do-your-research)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/do-your-research"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/do-your-research.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.01580 |
| Opus 5 | $0.00060 | $0.00790 |
| Sonnet 5 | $0.00024 | $0.00316 |
| Haiku 4.5 | $0.00012 | $0.00158 |
Grade A, and why
do-your-research 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 yesterday.
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.
Do your research
A drift corrector for research discipline. The method, re-anchor, audit
the work in flight, correct forward, report, and the tone that firing this
is not an accusation, lives in
${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md.
Read it; this file adds only what is specific to research discipline.
The discipline this re-anchors
Research and verification before assertion. Resolve its source of truth
per the method doc's ladder: if the consuming project states a
research/verification discipline in its own CLAUDE.md or .claude/rules/,
re-anchor THAT. Otherwise re-anchor this portable baseline:
- Assert nothing you cannot point to a source for. A claim labelled "known", "obvious", or "from memory" is unverified until a fetched source or the live environment backs it.
- Verify every concrete specific. A path, filename, default, flag, signature, or any "standard/conventional X" is a claim. Check it against an authoritative source or the actual environment before stating it as fact, most critically right before the user acts on it.
- Frame the problem before reaching for a solution. Name what is actually being solved; do not let the first solution shape decide it.
- Never act on ambiguity. Surface the unknown and resolve it rather than assuming a value.
- Training-data recall is a starting point, not an answer. Treat it as unverified until confirmed from a current, authoritative source.
"An authoritative source" is a bar with three dimensions
Naming a source is not clearing the bar. A source has a tier. Tool output and docs fetched this turn outrank secondary synthesis; ungrounded recall does not clear the bar at all until it is promoted. A claim needs independent corroboration. Citations that trace back to one upstream pool are one source, not three. And a claim about anything that ships releases needs a recency check against the current upstream, because first-party docs lag their own releases.
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.
- yesterday First seen · 131 lines · 121 tokens per session scan A d4ea0428c625
do-your-research is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 1,580 once invoked, about $0.0006 per session on Opus 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.
stack-based-backtrack
For search with undo: explicit decision stack, backtracking when paths fail, depth-first exploration with state restoration.
build-priority-queue
For ordered processing: A search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
compose-small-helpers
For complex behavior: build from tiny functions, chain transformations, make code read like a pipeline of operations.