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 pjt222/agent-almanac --skill curate-collectiongit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/curate-collection)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/curate-collection"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/curate-collection/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/pjt222/agent-almanac/curate-collection"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/curate-collection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.02917 |
| Opus 5 | $0.00053 | $0.01458 |
| Sonnet 5 | $0.00021 | $0.00583 |
| Haiku 4.5 | $0.00011 | $0.00292 |
Grade A, and why
curate-collection 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 6d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curate Collection
Build, assess, and maintain a library collection through strategic acquisitions, systematic weeding, usage analysis, and responsive reader advisory.
When to Use
- You are building a new collection with a defined scope and budget
- An existing collection needs assessment for gaps, redundancies, or outdated materials
- Shelves are overcrowded and systematic weeding is needed
- Users request materials the collection does not hold
- You want to establish a formal collection development policy
Inputs
- Required: Collection scope (subject areas, audience, formats)
- Required: Budget (annual acquisitions budget or one-time allocation)
- Optional: Usage data (circulation statistics, hold requests, ILL requests)
- Optional: Community or institutional profile (demographics, curriculum, research areas)
- Optional: Existing collection development policy
Procedure
Step 1: Define the Collection Development Policy
Establish the guiding document for all acquisition and weeding decisions.
Collection Development Policy Template:
1. MISSION STATEMENT
What is the collection for? Who does it serve?
Example: "Support the undergraduate curriculum in the
humanities and social sciences with current and
foundational works."
2. SCOPE
+-------------------+------------------------------------------+
| Element | Definition |
+-------------------+------------------------------------------+
| Subject areas | List of disciplines collected |
| Depth levels | Basic, instructional, research, |
| | comprehensive, exhaustive |
| Formats | Print, ebook, audiobook, media, serial |
| Languages | Primary and secondary languages |
| Chronological | Current only, or retrospective |
| Geographic | Any focus area or exclusion |
+-------------------+------------------------------------------+
3. SELECTION CRITERIA (in priority order)
a. Relevance to mission and audience needs
b. Authority and reputation of author/publisher
c. Currency (publication date vs. field currency)
d. Quality of content (reviews, awards, citations)
e. Format suitability (print vs. digital)
f. Cost relative to budget and expected use
g. Representation: diversity of perspectives and voices
4. WEEDING GUIDELINES
- Frequency: annual review cycle
- Method: CREW/MUSTIE (see Step 4)
- Disposition: sale, donation, recycling
5. REVIEW SCHEDULE
- Policy reviewed and updated every 3 years
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.
- 6d ago First seen · 305 lines · 105 tokens per session scan A e4119722e50c
curate-collection is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 2,917 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
review-spec
Independent read-only review of a frozen Product half before engineering planning. Runs the exact Product checks in a clean context and returns only SPEC-REVIEW-PASS, SPEC-REVIEW-FAIL, or NEEDS-DESIGN with a content-bound receipt. Never edits the reviewed SPEC. Triggers: "review-spec", "review the spec", "review…
ship-roadmap
Found or continue a roadmap autopilot one stage per invocation. Default: human merge. --fullauto is invocation-scoped and uses the transient wrapper only after a fresh audit. Triggers: "ship-roadmap", "ship the roadmap", "autopilot this project".
workflow-status
Read-only workflow sensor: compute repository, roadmap, dependency, PR, finding, and recovery state, then emit the fixed machine envelope. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next", "state of the run".
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
plan
Enter the Plan phase of CocoBrew. Runs CocoSpec quality gate pre-flight, reads spec.md and discuss.md (if present), invokes Coco native plan mode as a mandatory gate, captures the approved plan to plan.md, creates initial flow.json template, and commits. Must have $spec completed first.
lean-debt
CocoLean shortcut debt ledger — harvests cocoplus: comment markers across the CocoPod and produces a ranked deferral report sorted by ceiling imminence and age.