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/guitaralchemist/ga/digestnpx skills add GuitarAlchemist/ga --skill digestgit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/digest)<a href="https://agentmods.dev/skills/guitaralchemist/ga/digest"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/digest.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 | $0.00068 | $0.01774 |
| Opus 5 | $0.00034 | $0.00887 |
| Sonnet 5 | $0.00014 | $0.00355 |
| Haiku 4.5 | $0.00007 | $0.00177 |
Grade A, and why
digest 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digest
Captures the meaningful state of the current session to
state/digests/latest.md. The Scripts/sessionstart-digest.ps1 hook reads
it on the next session start and emits it as additionalContext for the
model. Pairs with Scripts/precompact-digest.ps1 which provides a
metadata-only fallback when /digest isn't invoked before auto-compaction.
When to run
- Before compaction is imminent (context feels >60% full).
- At a natural breakpoint — after finishing a feature, before a risky operation, before handing off to another agent.
- Before launching long-running background work so the digest captures what you expect that work to do.
Do NOT invoke on every message or tool call. The digest is for meaningful state changes, not transcript capture.
What it captures
Git metadata is gravy. The value is in the content sections + the success_criteria field (Karpathy R4: "task complete != goal achieved").
---
schema_version: 1
session_id: <session_id, propagated from PreCompact stdin when known>
written_at: <RFC3339 UTC>
trigger: digest-skill
branch: <git branch>
head_sha: <short SHA>
head_subject: <commit subject>
open_pr: <"#N" or null>
last_model_update: <RFC3339 UTC>
success_criteria:
- criterion: "<testable assertion for the Next action>"
status: pending | in-progress | achieved | abandoned
evidence: "<file:line | PR# | metric path | null>"
---
# Session digest — <branch> @ <sha>
## Next action
ONE imperative sentence describing the next concrete step. If multiple
things are queued, pick the one with highest blast radius. If nothing is
queued, write `Wait for user direction on <specific question>`.
The next action must map 1:1 to entries in the `success_criteria`
frontmatter array — each criterion testable, not vibes.
## In-flight
Bulleted list of work currently mid-execution. For each item: the
file/feature, the current step number out of total, and the immediate
next sub-step.
## Live hypotheses
Bulleted list of working hypotheses the next session should inherit.
"X is the bottleneck because Y" / "If we change A, B should follow."
These are *unconfirmed*; do not promote to MEMORY.md until validated.
## Open questions
Numbered. Questions you would ask the user if they walked in right now.
## Do NOT carry forward
**Highest-leverage field.** Things the next session must NOT re-propose:
rejected designs, abandoned approaches, paths the user explicitly closed.
Without this, a fresh model context will silently re-derive bad ideas you
already filtered.
## Prior success criteria status (Karpathy R4)
When a prior digest exists, this section reports the status delta:
- ✅ achieved: — evidence: <file:line | commit | PR>
- ⏳ in-progress: — last touched:
- ⛔ abandoned: — reason:
Carrying forward only the still-pending or in-progress criteria into the
new `success_criteria` frontmatter prevents drift.
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 First seen · 179 lines · 68 tokens per session scan A df1b48c0c67f
digest is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,774 once invoked, about $0.0003 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…