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/seldonframe/reflect/reflectnpx skills add seldonframe/reflect --skill reflectgit clone --depth 1 https://github.com/seldonframe/reflectWhat 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 | $0.00112 | $0.01782 |
| Opus 5 | $0.00056 | $0.00891 |
| Sonnet 5 | $0.00022 | $0.00356 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade A, and why
reflect 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
37 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.
- references/00-index.md 5.7 KB
- references/algorithms-bias.md 4.0 KB
- references/availability-bias.md 3.1 KB
- references/best-case.md 3.2 KB
- references/bezos-type1-type2.md 3.4 KB
- references/bikeshed.md 2.8 KB
- references/break-the-chain.md 3.4 KB
- references/captaincy.md 3.2 KB
- references/chestertons-fence.md 3.5 KB
- references/decision-anatomy.md 3.9 KB
- references/decision-matrix.md 3.3 KB
- references/defensive-decisions.md 3.2 KB
- references/dhh.md 6.9 KB
- references/explore-exploit.md 3.2 KB
- references/externalities.md 3.4 KB
- references/first-principles.md 3.4 KB
- references/gian-carlo-rota.md 3.5 KB
- references/hemingway-suitcase.md 3.4 KB
- references/inversion-avoid-stupidity.md 4.3 KB
- references/mark-pincus.md 6.0 KB
- references/mental-models-general.md 6.7 KB
- references/musk-algorithm.md 6.5 KB
- references/musk-founder-hardness.md 5.8 KB
- references/musk-physics-thinking.md 7.2 KB
- references/musk-speed.md 6.6 KB
- references/musk-truth-loop.md 6.3 KB
- references/ooda-loop.md 3.6 KB
- references/optionality.md 3.3 KB
- references/outliers-best-2025.md 5.5 KB
- references/peter-kaufman.md 5.6 KB
- references/probability-errors.md 3.7 KB
- references/slack.md 3.1 KB
- references/steve-wozniak.md 4.6 KB
- references/tobi-lutke.md 4.5 KB
- references/vlad-tenev.md 4.2 KB
- references/winston-weinberg.md 4.7 KB
- references/worst-day.md 3.0 KB
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.
- 2d ago First seen · 143 lines · 112 tokens per session scan A 68ccdae446f7
reflect is a skill published in the GitHub repository seldonframe/reflect (13 stars, last pushed 1mo ago), with no licence file. It adds 112 tokens to every session and 1,782 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 2026-08-30.
Other skills, from other repositories
blindspot-check
Checks a big decision for blind spots against a catalogue of 95 cognitive biases before the user commits. Use when the user is about to make or has just justified a major life decision and wants to be checked for self-deception — buying a house, relocating, signing a long lease or contract, quitting or taking a job…
thinking-toolkit
A toolkit of 30 decision-making, problem-solving, systems-thinking, and communication models, plus a /logic mode that audits an argument's validity. This skill should be used when a user names a specific model, or describes a situation that calls for one: framing or reframing a problem, comparing options, setting…
expert-engine
Core cognitive engine based on Gary Klein's RPD model. Load with any expert- skill for structured thinking analysis. Use when you need systematic expert-level analysis of decisions, problems, or situations.
expert-kahneman
Daniel Kahneman's behavioral economics and cognitive bias framework. Load with expert-engine for decision quality audits, bias detection, planning calibration, and debiasing strategies. Covers System 1/2, WYSIATI, Prospect Theory, and major heuristics.
expert-munger
Charlie Munger's mental models and decision frameworks. Load with expert-engine for investment, business decisions, and avoiding mistakes. Emphasizes inversion, incentive analysis, and multi-disciplinary thinking.
expert-graham
Paul Graham's frameworks for startups, ideas, and building products. Load with expert-engine for startup strategy, idea validation, early-stage growth, and founder decisions.