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/gregmos/memoforge/statusnpx skills add gregmos/memoforge --skill statusgit clone --depth 1 https://github.com/gregmos/memoforgeWhat 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 | $0.00038 | $0.01880 |
| Opus 5 | $0.00019 | $0.00940 |
| Sonnet 5 | $0.00008 | $0.00376 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
status scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memoforge / status skill
Read-only inspection of memoforge task state. Never mutate state.json. Never dispatch worker subagents. Never run python scripts. Only Read and Bash (for ls).
Output format — file references via Cowork artifact cards
This skill is read-only. To give the user clickable access to files, call the Read tool on each file you want to surface — Cowork's UI inserts an artifact card above your next message for any Read tool call, which is the user's clickable affordance. Then print plain-text paths in the report body so the user knows where things live on disk.
Path display in chat text uses state.json.rel_work_dir (canonical CWD-relative path field set by skills/memo/SKILL.md Phase 1 Task setup). If a legacy task is missing this field, compute it on the fly via:
REL_WORK_DIR=$(realpath --relative-to="$(pwd)" "$WORK_DIR" 2>/dev/null \
|| python3 -c "import os.path,sys; print(os.path.relpath(sys.argv[1]))" "$WORK_DIR" 2>/dev/null \
|| python -c "import os.path,sys; print(os.path.relpath(sys.argv[1]))" "$WORK_DIR" 2>/dev/null \
|| echo "$WORK_DIR")
(This skill is read-only — do NOT write the recomputed value back to state.json; just use it inline for the chat output.)
Do not wrap file paths in markdown link syntax. Cowork does not render relative or absolute paths as clickable file references inside chat text — clickability comes from the Read tool's artifact cards. Print all paths as plain text and rely on the Read calls for click access.
Parse argument
Read $ARGUMENTS.
Empty argument — list all tasks
- Scan the four canonical output-folder candidates (same resolution order as
skills/continue/SKILL.mdTask discovery):$CLAUDE_PLUGIN_OPTION_OUTPUT_FOLDER,$MEMOFORGE_OUTPUT_FOLDER,$HOME/Documents/memoforge,outputs/memoforge-work. For each parent that exists, runls "$parent"/memo-* 2>/dev/nulland collect uniquetask_iddirectories (a task_id appearing in two parents is deduped, but record the resolved parent path per task). - For each found
memo-*directory:- Read
state.json. - Extract
task_id,current_phase,created_at,user_query(first 100 chars),final_statusif set, andrel_work_dir(compute if absent).
- Read
- For each found task, call
Readon<resolved_path>/state.json— Cowork will insert an artifact card so the user can click to inspect each one. - Then print a plain-text table summarizing what was read:
| task_id | phase | created | query | path | |--------------------------------------------------|------------------------|---------------------|--------------------------------------|-------------------------------| | memo-2026-05-14T10-30-00-gdpr-biometrics-minors | revision_loop | 2026-05-14 10:30:00 | Can our product process biometr... | <rel_work_dir>/ |
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.
- 2d ago First seen · 122 lines · 38 tokens per session scan A 078d7d0514fd
status is a skill published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,880 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 2026-08-30.
Other skills, from other repositories
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
mod-actions
Comprehensive moderation toolkit: user actions (ban/mute/DM), strike system, image moderation, report handling, generation moderation, content/training moderation, and NCMEC/CSAM reporting. All via Civitai tRPC API.
auditing-part11-trails
Generates and verifies 21 CFR Part 11-style audit trails — who/what/when, electronic signatures, and tamper-evidence — for OpenMed pipelines in GxP and clinical-trial (GCP) settings. Use when the user runs OpenMed in a regulated/validated environment and needs an attributable, time-stamped, tamper-evident record of…
2026-legal-research-agent
Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic…
amazon-suspension-appeal
Account suspension prevention and appeal — policy violations, Plan of Action writing, reinstatement process.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…