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 commands/paveltkachenk0/contexttax/sync-memorygit clone --depth 1 https://github.com/PavelTkachenk0/ContextTaxWrote 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/commands/paveltkachenk0/contexttax/sync-memory)<a href="https://agentmods.dev/commands/paveltkachenk0/contexttax/sync-memory"><img src="https://agentmods.dev/badge/commands/paveltkachenk0/contexttax/sync-memory.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 | $0.00014 | $0.00291 |
| Opus 5 | $0.00007 | $0.00146 |
| Sonnet 5 | $0.00003 | $0.00058 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
sync-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Fold the outcomes of the most recent superpowers cycle back into the memory bank. This is the Definition of Done for every cycle.
- Find the most recent plan in
docs/superpowers/plans/(and its spec indocs/superpowers/specs/). If$ARGUMENTSnames a specific plan, use that. - Review what was actually built (git log / diff since the cycle started).
- Propose minimal edits to
.claude/memory-bank/:roadmap.md— mark the sub-project/feature done; set "Next". Always.architecture.md— if components / boundaries / dependencies changed.decisions/— a new ADR (use the/adrtemplate) for any notable decision not yet recorded.conventions.md— only if a new convention/pattern was established.
- Show the proposed diffs and apply after confirmation.
- Do not copy raw plan prose into the memory bank — distill. Plans are the journal; the memory bank is the current truth.
Targets layer 2 (the in-repo project memory bank), not layer 1 (personal memory — that
is the consolidate-memory skill).
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 · 23 lines · 14 tokens per session scan A 15d80eac1ae9
sync-memory is a command published in the GitHub repository PavelTkachenk0/ContextTax (5 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 291 once invoked, about $0.0001 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 commands, from other repositories
contextd-eval
Aggregate trace JSON từ nhiều run dưới {projectdir}/.contextd/runs/ → 1 báo cáo Markdown đo hiệu quả wiki: coverage, hallucination rate, top knowledge gaps, context-selector block rate, violation hotspots.
README
Đây là slash commands cho workflow contextd-aware. Trong migration window chúng vẫn cài dưới .claude/commands, nhưng canonical engine/config là contextd CLI + /.contextd/config.json. Pipeline kiến trúc tổng thể: agents/pipeline/README.md.
vault
Build/refresh a unified Obsidian vault (knowledge + all repo wikis).
recall
Recall what carryover already knows about a topic.
crusts
Run the CRUSTS context window analyzer and give me actionable advice.
dream
Run a curator pass over the memory dir. Produces a proposal artifact for /dream-apply. Default curator: rot.