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/nickcirv/engram/costnpx skills add NickCirv/engram --skill costgit clone --depth 1 https://github.com/NickCirv/engramWrote 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/nickcirv/engram/cost)<a href="https://agentmods.dev/skills/nickcirv/engram/cost"><img src="https://agentmods.dev/badge/skills/nickcirv/engram/cost.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 | $0.00040 | $0.00608 |
| Opus 5 | $0.00020 | $0.00304 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
cost scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- cost — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
engram cost
Show token-savings telemetry from engram's hook log. Three modes:
- Default — terminal table for the current project:
engram cost - Multi-project — across many roots:
engram cost -p /path/a -p /path/b - Weekly digest — Markdown file at
~/.engram/cost-report-YYYY-Www.md:engram cost --digest
Run the requested mode and report the totals:
- Tokens saved (numeric, with K/M suffix)
- Reduction ratio (percentage)
- Approximate USD saved (Claude Sonnet 4.6 input pricing by default)
- Total events (number of intercepted tool calls)
If the user passed "$ARGUMENTS", treat it as flag input (e.g., --digest, -p /path).
If the table shows zeroes, explain that historic events don't carry the new tokens-saved fields — real numbers populate within ~24 hours of v3.3 install.
Example invocations
User: "How much has engram saved me this week?"
You: Run engram cost --digest. Read the output. Quote the totals: tokens saved, reduction ratio, approx USD. Mention the digest file path so the user can paste it into Slack.
User: "Show me my engram numbers across all projects"
You: Multi-project mode. Run engram cost -p ~/proj-a -p ~/proj-b -p ~/proj-c (substitute with the user's actual paths if they list them, otherwise default to the current directory).
User: "Is engram even doing anything?"
You: Run engram cost --json and pipe to a sanity check. If events > 0 but tokensSaved == 0, the user is on engramx older than 3.3.0 — recommend npm i -g engramx@latest. If events == 0, the hook isn't installed — recommend engram install-hook.
User: "Compare cost vs last week"
You: Two digest files at ~/.engram/cost-report-YYYY-W{N}.md and ~/.engram/cost-report-YYYY-W{N-1}.md. Read both, present the deltas in a table.
When NOT to fire this skill
- The user is asking about npm package costs, hosting bills, or general cloud spend. This skill is engram-specific only.
- The user wants to set up cost tracking for the first time. Point them at
engram setupandengram install-hookfirst; cost data accumulates after the hook is wired.
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 · 42 lines · 40 tokens per session scan A 94c41b03ae97
cost is a skill published in the GitHub repository NickCirv/engram (141 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 608 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
chatcrystal-task-writeback
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
chatcrystal-task-recall
Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the…
forensic-deepdive-extract
Run a full forensic deep-dive on an unfamiliar codebase, producing five durable markdown artifacts (MAP.md, HOTPATHS.md, ARCHAEOLOGY.md, MENTALMODEL.md, AGENTBRIEF.md). Use when the user says "analyze this repo", "onboard me to X", "I just joined a new team", "deep-dive this codebase", or clones/opens a repo they…
forensic-deepdive-query
Answer questions about the current repo by querying its existing forensic-deepdive artifacts (MAP.md, HOTPATHS.md, ARCHAEOLOGY.md, MENTALMODEL.md, AGENTBRIEF.md). Use when the user asks "where does X live", "who owns Y", "how did Z evolve", "what should I touch to add a new W" — AND the repo already has these…
forensic-deepdive-update
Incrementally refresh forensic-deepdive artifacts after the codebase has changed. Use when MAP.md or HOTPATHS.md is stale (>7 days or >50 commits old), or after a significant refactor when the user wants artifacts to reflect reality. Do NOT use for first-time analysis (use forensic-deepdive-extract) or simple lookups…