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/clever-cc-plugins/cc-content/session-wrapnpx skills add clever-cc-plugins/cc-content --skill session-wrapgit clone --depth 1 https://github.com/clever-cc-plugins/cc-contentWhat 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 | $0.00066 | $0.02912 |
| Opus 5 | $0.00033 | $0.01456 |
| Sonnet 5 | $0.00013 | $0.00582 |
| Haiku 4.5 | $0.00007 | $0.00291 |
Grade C, and why
session-wrap scanned grade C with 2 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/learnings.md 2>/dev/null Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/_shared/persuasion-principles.md .claude/skills/_shared/storytelling-frameworks.md 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Wrap Skill
You are closing out a content creation session. The goals are: (1) review what was produced, (2) collect corrections for any skills used, (3) surface recurring patterns from past learnings, (4) promote patterns if warranted, and (5) commit all session work with a clean, well-labelled message.
Step 0: Recall learnings
If .claude/learnings.md exists, read it silently. This ensures pattern detection
in Step 5 operates on the most current state of the file. Do not announce this step.
If the file is absent, continue normally.
Step 1: Review deliverables
Run git status to understand what changed during the session:
git status --short
If git status reports no changes:
"No changes detected in git. Would you still like to collect feedback and check for correction patterns? (yes / no)"
If the owner says no, skip to Step 5. If yes, continue but skip the file summary.
If changes exist, group them into four categories and present them:
─────────────────────────────────────────────
Session deliverables
─────────────────────────────────────────────
Context files (registered context location, e.g. context/):
<list of modified/untracked files in the registered context location>
Deliverables (content output files):
<list of modified/untracked files that are not in .claude/ or skill folders>
Skill files (.claude/skills/):
<list of modified/untracked files in .claude/skills/>
Other:
<any remaining files>
─────────────────────────────────────────────
Omit any empty categories. If all changes are in a single category, still use the labelled format so the owner sees what type of work was done.
Step 1b: Promote deliverables to context
Look at the deliverables listed in Step 1 — files that are not in the
registered context location, .claude/, or skill folders.
If any deliverables were created or significantly modified, ask:
"Are any of these worth registering as context for future work? For example: a completed whitepaper, evergreen guide, or reference piece — something skills should be able to build upon later. (Name the files, or say 'none' to skip.)"
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.
- yesterday First seen · 345 lines · 66 tokens per session scan C b2089b6a927e
session-wrap is a skill published in the GitHub repository clever-cc-plugins/cc-content (1 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 2,912 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
feature-radar-archive
Archive a completed, rejected, or covered feature into .feature-radar/archive/ with mandatory learning extraction. MUST use this skill whenever a feature reaches a terminal state — done, rejected, covered, deferred, or N/A. Even casual mentions like "we shipped X" or "X is done" should trigger this. The skill extracts…
html-ppt-zhangzara-cartesian
An economics senior thesis on the employment effects of local minimum-wage increases — identification strategy, evidence, and limitations. Built as a decision-grade coursework defense deck for thesis committee.
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
digital-eguide
A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). Lifestyle / creator brand tone. Use when the brief asks for an "e-guide", "digital guide", "lookbook", "lead magnet"…
docs-page
A documentation page — inline-start nav, scrollable article body, inline-end table of contents. Use when the brief mentions "docs", "documentation", "guide", "API reference", or "tutorial".