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 jonny981/claude-tandem --skill recall-promotegit clone --depth 1 https://github.com/jonny981/claude-tandemWrote 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/jonny981/claude-tandem/recall-promote)<a href="https://agentmods.dev/skills/jonny981/claude-tandem/recall-promote"><img src="https://agentmods.dev/badge/skills/jonny981/claude-tandem/recall-promote/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/jonny981/claude-tandem/recall-promote"><img src="https://agentmods.dev/badge/skills/jonny981/claude-tandem/recall-promote.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 | $0.00036 | $0.00274 |
| Opus 5 | $0.00018 | $0.00137 |
| Sonnet 5 | $0.00007 | $0.00055 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
recall-promote 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 12d 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
Recall Promote
Review ~/.tandem/state/recurrence.json and the project MEMORY.md.
For each theme with count >= 3:
- Check if MEMORY.md already covers it
- If not, draft a [P1] entry with (observed: first_seen_date) capturing the theme's meaning
- Present proposed entries for user approval
- After approval, append to MEMORY.md
Output format
For each theme that needs promotion:
Theme: <slug> (count: N, first seen: YYYY-MM-DD)
Status: [already covered | needs promotion]
Proposed entry: [P1] <description> (observed: YYYY-MM-DD)
If all themes are already covered, report: "All recurring themes are represented in MEMORY.md."
Notes
- Only promote themes, never demote existing [P1] entries
- Use the theme slug's natural language form in the entry (e.g., "error-handling" becomes "error handling")
- The (observed: date) should use the theme's first_seen date from recurrence.json
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.
- 12d ago First seen · 32 lines · 36 tokens per session scan A 5fc568545c3e
recall-promote is a skill published in the GitHub repository jonny981/claude-tandem (6 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 274 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
memory-protocol
A shared set of rules for using a persistent memory service across coding-agent sessions.
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
context-management
Use in long or noisy sessions to persist durable state across session boundaries via state.md. Also generates project-map.md when asked to map the project. Triggers on: user explicitly asks to "save state", "compress context", "map this project", "generate project map", "create project map", cross-session handoff…
claude-md-creator
Creates minimal, high-signal CLAUDE.md and AGENTS.md context files based on empirical best practices. Invoke on /init command, "create CLAUDE.md", "update CLAUDE.md", "write AGENTS.md", or "set up Claude Code for this project". Also invoked by brainstorming when repo lacks a context file. tools: Read, Glob, Grep…
error-recovery
Maintains a project-specific known-issues.md mapping recurring errors to their solutions. Consulted automatically by systematic-debugging before investigation. Saves time by avoiding rediscovery of known problems across sessions. Triggers on: "save this fix", "remember this error", "known issues", or automatically…
session-summary
Summarize recent Caushell shell-session findings for the current Claude workspace.