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/3243dwon/clear-eye/forensic-readnpx skills add 3243dwon/clear-eye --skill forensic-readgit clone --depth 1 https://github.com/3243dwon/clear-eyeWrote 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/3243dwon/clear-eye/forensic-read)<a href="https://agentmods.dev/skills/3243dwon/clear-eye/forensic-read"><img src="https://agentmods.dev/badge/skills/3243dwon/clear-eye/forensic-read.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 | $0.00170 | $0.01320 |
| Opus 5 | $0.00085 | $0.00660 |
| Sonnet 5 | $0.00034 | $0.00264 |
| Haiku 4.5 | $0.00017 | $0.00132 |
Grade A, and why
forensic-read 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 4d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forensic Read
A summary tells you what a document says. A forensic read tells you what it's avoiding saying.
Treat the text like a witness statement: assume every word was chosen on purpose, and that the choices are evidence. The goal is not paranoia — it's noticing the gap between what was stated, what was implied, and what was conspicuously left out.
Core principle
Don't ask "what does this document say?" Ask "what would I expect an honest, complete version to contain — and what's missing or hedged?"
The read process
- Surface read. State plainly what the document claims, in one or two sentences. This is the baseline everything else is measured against.
- Collect evidence. Go through the text for the tells below. Quote them. (For longer texts, run
scripts/scan.pyfirst — see below — to ground this in numbers.) - Find the gap. What would a complete, candid version include that this one doesn't? Missing numbers, unnamed actors, undated promises, unanswered questions.
- Separate evidence from inference. Facts about the text (it hedges, it omits the salary) are evidence. What you think it means is inference. Always label which is which.
- Render the bottom line. One honest paragraph: what's really going on, and how confident you are.
What to hunt for
- Hedging / weasel words — "we believe", "aims to", "up to", "many", "generally". Density of deniability.
- Conspicuous omissions — the number that should be there and isn't; the question dodged; the actor never named.
- Buried leads — the most important fact placed in paragraph nine, in a subordinate clause.
- Frequency tells — what gets repeated obsessively (reassurance is often anxiety).
- Tone shifts — where confident prose suddenly goes vague or passive. That seam is usually where the body is buried.
- Non-answers — answering a question that wasn't asked; reframing instead of responding.
- Passive voice that hides the actor — "mistakes were made" by whom?
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.
- 4d ago First seen · 93 lines · 0 tokens per session scan A 48da2c03c78e
forensic-read is a skill published in the GitHub repository 3243dwon/clear-eye (1 stars, last pushed 3mo ago), licensed MIT. It adds 170 tokens to every session and 1,320 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-red-team
For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-circle-of-competence
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.