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/sunil-goyal-1502/project-memory/memory-savenpx skills add sunil-goyal-1502/project-memory --skill memory-savegit clone --depth 1 https://github.com/sunil-goyal-1502/project-memoryWrote 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/sunil-goyal-1502/project-memory/memory-save)<a href="https://agentmods.dev/skills/sunil-goyal-1502/project-memory/memory-save"><img src="https://agentmods.dev/badge/skills/sunil-goyal-1502/project-memory/memory-save.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 | $0.00005 | $0.00461 |
| Opus 5 | $0.00003 | $0.00230 |
| Sonnet 5 | $0.00001 | $0.00092 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
memory-save 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.
What it actually says
Save a Project Decision
Save an explicit decision to the project's canonical decision store.
Steps
-
Parse the decision text from
$ARGUMENTS.- If
$ARGUMENTSis empty or blank, ask the user what decision they want to save.
- If
-
Verify
.ai-memory/decisions.jsonlexists in the project root.- If not, tell the user to run
/project-memory:memory-initfirst.
- If not, tell the user to run
-
Generate a decision entry as a single JSON line:
{ "id": "<8-character random hex string>", "ts": "<current ISO8601 timestamp>", "category": "explicit", "decision": "<the decision text from $ARGUMENTS>", "rationale": "Explicitly saved by user", "confidence": 1.0, "source": "manual" }Generate the 8-char hex ID and ISO timestamp. Then append this as a single line to
.ai-memory/decisions.jsonl.Use Bash to append:
echo '{"id":"<hex>","ts":"<iso>","category":"explicit","decision":"<text>","rationale":"Explicitly saved by user","confidence":1.0,"source":"manual"}' >> .ai-memory/decisions.jsonl -
Run sync to update all tool-specific files:
node -e "require('${CLAUDE_PLUGIN_ROOT}/scripts/sync-tools.js').syncAll(process.cwd())" -
Confirm to the user what was saved and that all tool files were updated.
-
Show projected savings: Display:
"This decision will save ~150 tokens and ~15 seconds each time it's loaded in a future session."Then show cumulative stats:
node -e "const s=require('${CLAUDE_PLUGIN_ROOT}/scripts/stats.js');const st=s.getStats(process.cwd());console.log(s.formatStatsLine(0,0,st))"
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 · 52 lines · 5 tokens per session scan A ca75f4582ceb
memory-save is a skill published in the GitHub repository sunil-goyal-1502/project-memory (8 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 461 once invoked, about $0.0000 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
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…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
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…