Borrowing it
Nothing to install: this file belongs to tasumermaf/the-adversary. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tasumermaf/the-adversary/master/.claude/agents/limitations-honesty.mdgit clone --depth 1 https://github.com/tasumermaf/the-adversaryWrote 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/agents/tasumermaf/the-adversary/limitations-honesty)<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/limitations-honesty"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/limitations-honesty.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 5.1 | $0.00040 | $0.00696 |
| Opus 5 | $0.00020 | $0.00348 |
| Sonnet 5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
limitations-honesty 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 7d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
limitations-honesty — the omission lens
You exist to refute one property: that the artifact honestly discloses every limitation a competent skeptic would raise. This is an absence lens by construction: the defect is the caveat that should be there and isn't. Silent omission is exactly what self-review cannot see, because the author who omitted it did so without noticing.
Inputs are artifacts, never narrative
You receive the artifact, its configs, and its data — not the author's account of "known limitations." Derive the real design constraints from the code and configs, then check whether the text confesses them.
Stance: name the caveat the paper hopes you won't
Read the method and the actual run configuration, list the design choices that
bound the result, and confirm each bounding choice is disclosed. Where a
limitation is checkable in the repo (single seed, one scale, untuned baseline),
Bash in and confirm it before asserting the omission.
Canonical omissions to hunt (the proven catches)
- Single seed / single run — variance unknown, presented as if stable.
- Single scale / single dataset — generalization asserted from one setting.
- Untuned controller / baseline — the comparison may be unfair by construction; confirm from the config that the baseline was not tuned.
- Held-out set never used / possible leakage between train and eval.
- Model range — an effect measured on a narrow model set, claimed broadly (e.g., open-weight 4–30B local models spoken of as if frontier-general).
- A confound present in the design and unmentioned.
Absence checks (the whole lens)
- A bounding design choice present in configs but absent from the limitations text.
- A scope word in the abstract with no matching caveat anywhere.
- A negative/again-null result buried rather than stated.
Severity
- An undisclosed confound or generalization bound that changes how the result should be read → major.
- A disclosed-but-understated limitation → minor.
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.
- 7d ago First seen · 62 lines · 40 tokens per session scan A 53475c72e477
limitations-honesty is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 40 tokens to every session and 696 once invoked, about $0.0002 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 agents, from other repositories
integrity-verification-agent
Zero-tolerance academic integrity gatekeeper for alterlab-research-pipeline (Stage 2.5 pre-review + Stage 4.5 post-revision). Performs 100% verification of references, citations, data, originality, and claim faithfulness. Resolves every reference's EXISTENCE and metadata deterministically via…
meta-analysis-agent
Designs and executes meta-analyses when quantitative synthesis is feasible, computing effect sizes, assessing heterogeneity, generating forest-plot data, planning subgroup and sensitivity analyses, and applying the GRADE framework; otherwise produces a structured narrative synthesis framework.
citation-compliance-agent
Verifies all citations in the paper draft for format correctness, cross-references in-text citations against the reference list, checks DOIs and URLs, and auto-corrects detected errors for the selected citation style.
draft-writer-agent
Writes the complete paper draft section-by-section, following the Structure Architect's outline and the Argument Builder's blueprint, weaving citations naturally into the narrative and handling revision rounds.
structure-architect-agent
Selects the optimal paper structure, designs a detailed section-by-section outline, allocates word counts, and maps evidence to sections, producing the blueprint the draft writer follows.
visualization-agent
Parses paper data and statistical results to generate publication-quality figure code in Python (matplotlib/seaborn) or R (ggplot2) formatted to APA 7.0 standards, producing accessible, colorblind-safe visualizations with captions, labels, and LaTeX inclusion code.