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/tmj-90/gaffer/memory-onboardnpx skills add tmj-90/gaffer --skill memory-onboardgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/memory-onboard)<a href="https://agentmods.dev/skills/tmj-90/gaffer/memory-onboard"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/memory-onboard.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 | $0.00196 | $0.03603 |
| Opus 5 | $0.00098 | $0.01801 |
| Sonnet 5 | $0.00039 | $0.00721 |
| Haiku 4.5 | $0.00020 | $0.00360 |
Grade A, and why
memory-onboard 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/memory-onboard — repo-aware onboarding for memory
This skill is the way to seed a repo with lore. It earns its keep by reading the repo first (README, ADRs, recent commits, deprecation markers, in-flight migrations) so the proposed drafts are specific to this codebase, with source citations — rather than inventing memory or mechanically chunking every bullet in the docs (which produces mostly noise and floods the review queue).
Output: DRAFT records with source citations, plus optional absence
markers and boundary edges. Everything lands in memory review for a
human to ratify — the skill never promotes its own records.
Hard rules
- Every lore record this skill produces is a DRAFT. Call
suggest_lore(orreport_conflictfor counter-claims — also drafts), never any approval path. The human reviews withmemory review. Exception:record_absencedoes NOT create a draft — it records a self-expiring "we checked, no policy" marker. Different primitive, different gate (see rule 6). - Every draft carries the tag
inductionso it can be filtered later. Layer topic-specific extras as appropriate (security,conventions,migrations,incident-lessons,invariants, etc.).report_conflictcounter-drafts are auto-taggedconflict-reportby the server. - Cite sources in the body. When a draft comes from a file or commit,
include a one-line reference at the top of the
body— e.g.Source: README.md L42–55orSource: commit abc1234 "migrate accounts → organisations". This is the trust signal a reviewer needs. - Never put secrets, credentials, personal data, regulated data, or anything that looks like a token into any lore record. If a candidate item contains something like that, skip it and tell the user why.
- Skip the obvious. "We use TypeScript", "run the tests before
committing", and other things a model already knows about a typical
codebase belong in
CLAUDE.md(or nowhere), not in lore. Aim for non-obvious, high-consequence knowledge. - Use
record_absencesparingly. If the user explicitly confirms "we don't have a policy on X yet, and that's intentional", that's a legitimate absence marker — callrecord_absence({ query: "<topic>", reason: "<why no policy>", repo: <repo> }). Don't infer absence from "I didn't find anything in the README"; the user has to confirm it. Markers self-expire (14 days default) so they fade automatically if the team takes a stance later. - Use
report_conflictwhen you find a contradiction, not when you find a duplicate. Ifsearch_lorereturns an existing record and the source-of-truth you just read disagrees with it (e.g. README says "Argon2id", existing lore says "scrypt"), that's areport_conflictmoment. If the existing record just covers the same topic without contradicting, leave it alone —possibleConflictsin search results handles benign overlap.
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 · 300 lines · 196 tokens per session scan A 6851503caf34
memory-onboard is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 196 tokens to every session and 3,603 once invoked, about $0.0010 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
session-cleanup
Backup old AnkaLoop sessions by renaming with execution date, then clean and compact sessions and memory.
session-handoff
Create consistent session handoff documents for context transfer between sessions. Use when closing a session, reaching 75% token consumption, or when user requests handoff. Ensures proper YAML headers for metrics collection, LF line endings, and complete documentation of progress, decisions, and next steps.
pact-recall
Search PACT's vector memory for relevant bugs, solutions, research, and feedback.
para-memory-files
File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns.…
context-engineering
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
context-compression
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.