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 sh5623/self-improvement --skill si-archivegit clone --depth 1 https://github.com/sh5623/self-improvementWrote 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/sh5623/self-improvement/si-archive)<a href="https://agentmods.dev/skills/sh5623/self-improvement/si-archive"><img src="https://agentmods.dev/badge/skills/sh5623/self-improvement/si-archive/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/sh5623/self-improvement/si-archive"><img src="https://agentmods.dev/badge/skills/sh5623/self-improvement/si-archive.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 | $0.00045 | $0.00614 |
| Opus 5 | $0.00023 | $0.00307 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
si-archive 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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive conventions in Codex
Read runtime boundaries and data resolution and format maps. Resolve actual paths before measuring; missing data is not a zero count.
Two independent entry conditions
- A: a document or log exceeds its project budget. Measure only the routed documents; without a routing map, measure the effective instruction doc and actual log and report other layers as unmeasured. Count the real record unit, not headings in examples.
- B: the caller or repair protocol names a dead/duplicate clause. Inspect that clause even when every document is below budget. This does not authorize unrelated cleanup.
Neither: finish with no cleanup needed.
Classify and move
For each triggered clause: demote to a narrower runtime-compatible home / merge into an existing canonical rule / archive a dead rule / keep a universally applicable rule. Support dead or exclusion judgments with actual references, removed targets, or replacing tool rules. Do not archive a rule solely because Codex does not consume a Claude file.
Preserve the original text, date and reason at the destination before removing source text.
Shared rules remain in shared docs; Codex-only demotion uses an applicable directory AGENTS
file or explicit task document. Do not create Claude paths: files as Codex instructions.
Update the actual migration table or registered equivalent. If no equivalent exists,
propose a record in the existing system's format before moving; inventing a table name
does not create a migration record.
If archive: none, propose the archive and moves, report overflow, and preserve source
clauses and logs. Do not perform destructive half-migrations.
Rotate and verify
For a configured archive and an over-cap log, move only the oldest overflowing work blocks
to the top of the archive log. Keep the complete index and migration history in the head.
Use the format map's real record unit and budget; default generated layout caps at 15. Measure
with the fence-aware count in data.md (or
scripts/count_log_blocks.sh), passing the map's unit and the log section's heading; a plain
grep -c of headings over-counts fenced examples and other sections.
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.
- 5d ago Changed · -42 lines · -68 tokens per session 7975cdb87589
- 12d ago First seen · 97 lines · 113 tokens per session scan A 6f9d60cbb8c9
si-archive is a skill published in the GitHub repository sh5623/self-improvement (1 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 614 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
align
Align a project to brana practices — assess gaps, plan, implement, verify. Auto-detects type. Use when setting up a new project or realigning an existing one.
recursive-spine-digest
Use when sweeping all recursive-spine-conforming repos for tracking health — aging deferrals (oldest first), stalled milestones, in-flight by lane, assigned-but-untouched issues, and debts named in closing comments but never filed, plus seedling pollen that never transplanted (hive repos). Reports honest denominators…
recursive-spine-scaffold
Use when a repo has (or is getting) the tracking stamp and needs the rest of its spine — interviews for and stamps up to six parts, each optional: a rules codex with a moments map, an ADR directory, a CI gate skeleton, a session-memory convention, a constraints file with its sha-pinned drift gate, and the loop…
recursive-spine-bootstrap
Use when installing the recursive-spine tracking convention onto a repo — interviews for modules and dialect, then stamps labels, issue/PR templates, a CLAUDE.md/AGENTS.md tracking section, and cross-project board membership. Idempotent; degrades loudly on missing gh scopes; offers (never forces) plumb-line and…
recursive-spine-handover
Use when closing a unit of work — an issue is about to close, a PR is about to merge, or a session is ending with its work complete. Assembles the closing record as a comment on the issue: debts filed before the close (principle 4), the pollen question asked, state pointers captured, the down-tier offer made. Previews…
recursive-spine-nudge
Use after a recursive-spine-digest sweep to select and deliver system-initiated nudges — 0–3 conversation-starters pushed to the owner about what is unblocked, aging, stalled, or newly connected. Every nudge ends in a question; the skill proposes conversations, never executes work.