Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frognpx agentmods add skills/nguyenthienthanh/aura-frog/plan-archivistWrote 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/nguyenthienthanh/aura-frog/plan-archivist)<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/plan-archivist"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/plan-archivist.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 5.1 | $0.00049 | $0.01142 |
| Opus 5 | $0.00024 | $0.00571 |
| Sonnet 5 | $0.00010 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
plan-archivist 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.
Plan Archivist
STATUS — v3.7.0-alpha.4. Compression companion to epic-summarizer.
Difference vs. epic-summarizer
| Concern | epic-summarizer | plan-archivist |
|---|---|---|
| Output | .claude/memory/permanent_memory.md (durable wisdom) |
.claude/plans/archive/{NODE_ID}.summary.md (plan-tree compaction) |
| Scope | Cross-cutting decisions + gotchas | Per-branch summary: what shipped, with what AC, what tasks |
| Lifecycle | Survives reset | Survives reset |
| Token budget | ≤500/Epic, ≤8000 total | ≤300/branch, no global cap (one file per archived branch) |
epic-summarizer captures what was learned. plan-archivist captures what was built.
Behavior
- Detect: caller passed
<NODE_ID>— must be T2 or T1, statusdone. Refuse otherwise. - Read the node + all descendants (Stories, Tasks).
- Compose archive summary:
- One-line intent
- Children summary (id, status, AC count, completion date)
- Acceptance criteria roll-up (passed/total per Story)
- Total tasks (done/discarded/skipped)
- Trace size + hallucination count (if traces exist)
- Write
.claude/plans/archive/{NODE_ID}.summary.md. - Optional pruning (only with
--pruneflag): remove the original Story/Task files (they're in checkpoints if needed). Refuse to prune if any descendant is not indoneorarchived. - Update parent's
childrenlist — replace pruned IDs with archive references. - Append
history.jsonlevent:event: branch_archived, with archive_path + pruned count.
Pruning rules
- Default: keep originals —
--pruneis opt-in - Always preserves
archive/{NODE_ID}.summary.mdeven if pruning fails midway - Never prunes the T1 Initiative or T0 Mission node (top-tier nodes accumulate, not archive-prune)
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.
- 3d ago First seen · 103 lines · 49 tokens per session scan A f5150125090f
plan-archivist is a skill published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,142 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 2026-09-03.
Other skills, from other repositories
gsd-capture
Capture ideas, tasks, notes, and seeds to their destination.
gsd-ns-ideate
Route to the appropriate exploration / capture skill based on the user's intent. gsd-note, gsd-add-todo, gsd-add-backlog, and gsd-plant-seed were folded into gsd-capture (with --note, default, --backlog, --seed modes) by #2790. The capture target lists pending todos via --list.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
recipe-front-design
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.
recipe-design
Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval.