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/blisspixel/primr/hypothesis-trackingnpx skills add blisspixel/primr --skill hypothesis-trackinggit clone --depth 1 https://github.com/blisspixel/primrWrote 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/blisspixel/primr/hypothesis-tracking)<a href="https://agentmods.dev/skills/blisspixel/primr/hypothesis-tracking"><img src="https://agentmods.dev/badge/skills/blisspixel/primr/hypothesis-tracking.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 | $0.00038 | $0.00291 |
| Opus 5 | $0.00019 | $0.00146 |
| Sonnet 5 | $0.00008 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
hypothesis-tracking 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.
What it actually says
Hypothesis Tracking
Purpose
Use this skill to manage durable research memory for a company. Hypotheses are a working memory layer, not final truth.
Workflow
-
Retrieve hypotheses before starting duplicate research.
-
Present confidence clearly: untested, validated, invalidated, or confirmed.
-
Update confidence only when new evidence exists.
-
Keep evidence strings short, factual, and source-oriented.
Operating Rules
-
Distinguish known facts from open hypotheses.
-
Preserve the evidence trail when confidence changes.
-
Prefer updating an existing hypothesis over creating duplicates.
-
Expired or weak hypotheses should be re-validated before being presented as current.
Example
get_hypotheses(company="ExampleCo", topic="technology")
save_hypothesis(company="ExampleCo", hypothesis_id="h_001", confidence="validated", evidence="CTO interview confirms AWS usage")
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 · 39 lines · 38 tokens per session scan A 20e6c72830dc
hypothesis-tracking is a skill published in the GitHub repository blisspixel/primr (3 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 291 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 skills, from other repositories
autosearch:experience-compact
Promote recurring patterns from experience/patterns.jsonl into the compact experience.md digest (≤120 lines, read by runtime AI before calling the skill). Triggers on N-events / file-size / user-feedback / session-end. Guards against single-success noise and pollution via promotion thresholds.
autosearch:context-retention-policy
Session-level policy for keeping the runtime AI's context window healthy across long research — keep-last-k tool results, offload older evidence to disk, trigger compaction at thresholds. Borrows MiroThinker's keeptoolresult, deepagents' summarization middleware, and deer-flow's SummarizationEvent pattern. Orthogonal…
memory-audit-pattern-extraction
模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用。.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.