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 agents/rlacombe/switchback-running/activity-memorygit clone --depth 1 https://github.com/rlacombe/switchback-runningWhat 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 | $0.00000 | $0.00416 |
| Opus 5 | $0.00000 | $0.00208 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
activity-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 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.
What it actually says
Activity Memory Procedure
Activity memory is enabled by default. Use this procedure after a review unless athlete/profile.md sets Activity memory to disabled, or when the athlete asks to archive, backfill, or retrieve a completed workout. An explicit archive request always proceeds.
- Identify the activity or requested date range. Prefer Intervals.icu when it is configured; otherwise use Strava. When both providers describe the same physical session, create one record with both source IDs rather than duplicates.
- Fetch compact activity detail. Retrieve streams only for a concrete analysis, such as heart-rate decoupling or climbing pacing. Do not retrieve route coordinates unless the athlete explicitly requests route analysis.
- Create or update
athlete/activities/YYYY/MM/YYYY-MM-DD--provider--activity-id.mdusingathlete/activity-note.example.md. - Retain source IDs, local start time and timezone, sport type, distance, duration, elevation, pace or speed, heart rate, training load, power/cadence, perceived exertion, gear, athlete-authored description when relevant, and short plan/execution/assessment sections.
- Preserve manually written narrative in an existing record. Put cross-workout patterns in
athlete/notes.mdonly when they are durable; activity-specific observations stay with the activity. - Do not retain GPX/TCX/FIT files, GPS coordinates, raw streams, or third-party comments and kudos. Those remain provider-side and are retrieved transiently only when useful and permitted.
- For a first historical backfill, ask the athlete to choose a lookback period (for example 1, 3, 6, or 12 months) before querying provider history. Never silently choose a period. Record the selected period and completion date in
athlete/profile.md. - Report the record path and whether it was created or updated. For a date range, report the count and any duplicate sessions reconciled.
See docs/activity-memory.md for the rationale and retention policy.
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 · 15 lines · 0 tokens per session scan A 7979e0b2c019
activity-memory is an agent published in the GitHub repository rlacombe/switchback-running (11 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 416 tokens. 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 agents, from other repositories
supply-chain-analyst
Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…
threat-modeler
Threat-modeling specialist using STRIDE, PASTA, and LINDDUN. Builds and updates data-flow diagrams, identifies trust boundaries, enumerates threats per element, and ties each threat to a concrete mitigation in code or process. Use PROACTIVELY when designing a new feature, evolving an existing system, authoring or…
devops-sre
Site reliability and deployment expert for ReasonKit infrastructure, CI/CD pipelines, Kubernetes orchestration, and zero-downtime production operations.
wtfp-research-synthesizer
Investigate the literature needed to plan and write a specific section well. The output is an evidence-traceable synthesis of foundational and recent work, standard approaches, genuine gaps, positioning options, and concrete writing guidance—not a search-result dump.
wtfp-section-writer
Execute an approved section plan into evidence-grounded academic prose or the explicitly requested scaffold. Preserve the author’s epistemic authority, make only supported claims, and leave an auditable account of what was produced and what remains unresolved.
wtfp-prose-polisher
Improve clarity, rhythm, concision, and authorial voice without changing technical meaning, evidence, citation placement, or argumentative direction. Polishing is a constrained transformation, not a substantive rewrite.