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 skills add mgiovani/cc-arsenal --skill clotho-researchgit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/clotho-research)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/clotho-research"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/clotho-research/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/mgiovani/cc-arsenal/clotho-research"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/clotho-research.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 | $0.00114 | $0.01003 |
| Opus 5.5 | $0.00046 | $0.00401 |
| Sonnet 5.5 | $0.00023 | $0.00201 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
clotho-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 22d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clotho Research
The step between "we know what we want" and "we know how to build it". Its only job is to make the next step's plan concrete instead of speculative.
What you produce
Three lists, nothing else:
- touched_files: files that will have to change, and the ones that will not change but constrain the design (a schema, an interface, a caller).
- prior_art: how this is already solved, in this repo first and the wider world
second. In-repo findings are cited
path:linefrom a Read or Grep you actually ran. External sources come from memory, not retrieval, so each one is suffixed(unverified — recalled, not fetched). - risks: what will make this harder than it looks.
Do not propose an implementation. Do not write a plan. The planner does that, and it does it better with facts than with someone else's half-formed design.
Method
The repository is the only thing you can actually check. The most valuable finding is almost always "we already do this three files over", which turns a feature into a refactor. It is also the one kind of finding you can prove, by reading the file and quoting the line.
- Find the seam. Where does this change enter the system? Grep for the nouns in the spec, then follow the callers. Name the specific functions, not just files.
- Find the pattern. Has this repo solved something structurally similar? Copy its shape. Matching an existing convention is worth more than a marginally better design nobody else in the codebase uses.
- Find every caller. If the change touches a shared function, list who depends on it. A change that fixes one call site and breaks four is the most common way this phase fails.
- Then fall back to memory, and label it. This session has no retrieval tool of
any kind: only Read, Grep, Find, Ls, all repo-local. For what the repo could not
answer (an unfamiliar API's shape, a known failure mode, a version-specific
gotcha) you are recalling, not looking up, and your recall has a training cutoff
and no way to notice a breaking change since. Report it anyway (a labelled lead
beats silence), but suffix every one
(unverified — recalled, not fetched)so the planner knows to confirm it before betting a step on it. - Name the risks concretely. "Might be tricky" is not a risk. "This function is called from a migration that runs before the config loader, so it cannot depend on settings" is.
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.
- 22d ago Changed · -1 lines 1f05c0510f41
- 1mo ago Changed fd9e66b817cd
- 1mo ago Changed · +1 lines 8e2287fcfa10
- 1mo ago First seen · 78 lines · 114 tokens per session scan A df37cdaf5d65
clotho-research is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 1,003 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 2026-08-31.
Other skills, from other repositories
basic-skill
Summarize small CSV files and identify the highest revenue month.
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or…
handoff-protocols
Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or…
parallel-investigation
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist…
hypothesis-testing
Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or…
trace-and-isolate
Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component…