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 Green-PT/honey-for-devs --skill honey-memorygit clone --depth 1 https://github.com/Green-PT/honey-for-devsWrote 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/green-pt/honey-for-devs/honey-memory)<a href="https://agentmods.dev/skills/green-pt/honey-for-devs/honey-memory"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-memory/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/green-pt/honey-for-devs/honey-memory"><img src="https://agentmods.dev/badge/skills/green-pt/honey-for-devs/honey-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.00818 |
| Opus 5.5 | $0.00006 | $0.00327 |
| Sonnet 5.5 | $0.00003 | $0.00164 |
| Haiku 4.5 | $0.00001 | $0.00082 |
Grade A, and why
honey-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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honey Memory
Lever 2 applied to discovery cost. Every cold session re-greps the same things — where auth lives, the build command, why X is shaped Y. One committed file replaces N rediscovery round-trips with a single cached read, on every future session. The cheapest token is the one not re-derived.
The win is per-session and recurring. The risk is staleness — a wrong cached fact costs more than no file. So the file lives in git, next to the code that can invalidate it, and is fixed in the same change that breaks it.
Scaffold (create)
- One file per repo:
PROJECT.mdat the root, committed (not~/.claude). If the repo already hasCLAUDE.md/AGENTS.md, add/refresh a## Memorysection there instead — don't add a second file. - Back up before overwriting an existing file: copy →
FILE.original.md. If that backup already exists, stop and ask. Never clobber a restore point. - Write only three kinds of fact (derive by reading the repo):
- Architecture + conventions an agent can't cheaply grep — where things live, and why (the intent, not the file list).
- Build / test / run commands, env, and gotchas.
- Decisions and dead-ends — choices made, paths tried and rejected. This is intent; it is never in the code.
- Report what was written and the file path.
Never store
- Anything derivable from source — code structure, symbol locations, past fixes, git history. Re-deriving is cheaper than maintaining, and never stale.
- Secrets, tokens, credentials. The file is committed.
- Transient state — open TODOs, this-week status. That rots fastest.
If a fact is stable + expensive-to-rediscover + not-in-the-code, write it. Everything else, let agents derive on demand — caching it is where these systems quietly lose money.
Update
A markdown file does not update itself. Reliability = discipline, not infra:
- Same-change rule (primary). When code changes invalidate a fact, fix the fact in the same commit. Review catches drift because the file is in git.
- On-demand refresh. Re-read the repo and rewrite stale entries; show the diff. Don't blind-append — appending is how these files bloat and rot.
- Treat a fact as superseded, not accumulated: replace the old line, don't stack a new one beside it.
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.
- 1mo ago First seen · 78 lines · 14 tokens per session scan A 79ccec5ad9d6
honey-memory is a skill published in the GitHub repository Green-PT/honey-for-devs (335 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 818 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
ctx
Use ctx as working memory for prior agent work. Before starting or continuing work in an unfamiliar area, resuming earlier work, or revisiting an investigation, search prior sessions to ground yourself in earlier context. Use ctx blame to trace a line, file, commit, or PR to the agent session that produced it. Use…
session-end
MUST use when user says 'bye', 'goodbye', 'good night', 'gnight', 'done for today', 'that's all', 'that's it', 'see you', 'see ya', 'let's stop', 'stopping here', 'wrapping up', 'signing off', 'closing down', 'done', 'finished for now', 'talk later', 'cya'. The user does NOT use slash commands; detect these natural…
save-session
MUST use when user says 'save', 'save session', or explicitly wants to preserve session state. {USERNAME} does NOT use slash commands; also trigger proactively when significant work has been completed and session context should be persisted. For session endings (bye/done/goodbye), use the session-end skill instead…
load-session
Restore session context at the start of every new conversation. Auto-triggers on session start, or when user says 'continue', 'what were we doing', 'where did we leave off'.
register-project
Register an existing project in memory. Use when starting work on a new repo or when a project needs its own context file. Triggers on: 'register project', 'add project to memory', 'track this project', 'create project file'.
memory-read
Query-first indexing and retrieval for Operator OS memory. Use when asked to find prior context, search memory, rebuild the memory index, or answer from the workspace without loading large files by default.