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 adaptocms/adapto-cms-agent-skills --skill adapto-project-learngit clone --depth 1 https://github.com/adaptocms/adapto-cms-agent-skillsWrote 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/adaptocms/adapto-cms-agent-skills/adapto-project-learn)<a href="https://agentmods.dev/skills/adaptocms/adapto-cms-agent-skills/adapto-project-learn"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-project-learn/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/adaptocms/adapto-cms-agent-skills/adapto-project-learn"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-project-learn.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 | $0.00068 | $0.01151 |
| Opus 5 | $0.00034 | $0.00575 |
| Sonnet 5 | $0.00014 | $0.00230 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
adapto-project-learn 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 9d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adapto:project-learn
The brain's consolidation step. While the content skills work, they append dated findings to
.adapto/project/learnings.md (capture fast). This skill does the deliberate half: it distills those raw
learnings into the structured facets (audience.md, seo.md, competitors.md, …) and closes resolved
items in open-questions.md, so the project brain genuinely improves over time instead of drifting. Local
only — no CMS writes — and it shows you a diff to approve before writing (the brain is your source of
truth; conventions.md §15 / studio.md).
When to use
- "Consolidate what you've learned", "update the project brain", "fold my notes into the brain".
- After a content cycle, or whenever
learnings.md/open-questions.mdhas grown.
When not to use
- Building the brain from scratch (interview + research) →
adapto:project-define. - Writing content → the content pipeline (
content-research→ … →content-upload). - Just checking the environment →
adapto:doctor.
Inputs
.adapto/project/learnings.md(the append-only capture log) andopen-questions.md.- The current facet files (
identity,audience,voice,glossary,competitors,pillars,seo,inventory) — to merge into, not overwrite.
Outputs
- Updated facet files reflecting the consolidated learnings.
open-questions.mdwith resolved items closed (and any new ones added).learnings.mdwith consolidated entries marked as consolidated (kept for history, not deleted) plus a dated consolidation note.- Next step: back into the flow — usually
adapto:content-researchfor the next cycle (now sharper), oradapto:content-planif research is still fresh.
Consolidation (review, then write — no CMS)
- Read
learnings.md+open-questions.md+ the facet files. - Distill (Sonnet-class): group raw learnings by facet; decide what each changes (a new audience pain, a keyword that converts, a competitor angle, a voice correction); identify which open questions are now answered.
- Show a diff of the proposed facet changes + which open-questions close + which learnings get marked
consolidated, and ask as a pickable question (
Approve/Change something/Discuss this). Because this rewrites a brain the user may have hand-edited, merge — never clobber — and surface anything ambiguous instead of guessing. - On approval, write the facet updates, close the open-questions, mark the consolidated learnings, and
append a dated
learnings.mdnote ("consolidated N items on<date>"). Then state what changed and propose the next step.
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.
- 9d ago First seen · 75 lines · 68 tokens per session scan A b84f97073401
adapto-project-learn is a skill published in the GitHub repository adaptocms/adapto-cms-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,151 once invoked, about $0.0003 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
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
recall
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
recall-reasoning
Recall the reasoning behind a past change by locating the Claude Code transcript that produced it. Use when the user asks to "recall reasoning", "find reasoning", "look up reasoning", "recall implementation reasoning", "find the rationale", "why did I do X", "recall from transcripts", or "find the transcript for this…
context-anchoring
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles).…