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 OutlineDriven/outline-driven-development --skill append-run-loggit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/append-run-log)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/append-run-log"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/append-run-log/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/outlinedriven/outline-driven-development/append-run-log"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/append-run-log.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 | $0.00034 | $0.01214 |
| Opus 5.5 | $0.00014 | $0.00486 |
| Sonnet 5.5 | $0.00007 | $0.00243 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
append-run-log 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 22d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Append run log
Contract
| Field | Bound contract |
|---|---|
| Trigger | A completed agent run must be recorded as durable, queryable evidence. |
| Authority | Reversible local: writes the run log, last-run pointer, and a same-directory temporary file during retention compaction; without retention it appends, and with retention it atomically removes expired entries while preserving retained lines byte-for-byte. Rollback is version control. No remote mutation. |
| Side effect | Appends one entry to the JSONL run log under an ISO-only date guard; when retention_window is supplied, atomically compacts away expired entries while preserving retained lines byte-for-byte, then updates the last-run pointer. |
| Done | Exactly one entry exists per run with a unique run id, malformed lines are ignored rather than corrupting the log, and aggregate metrics are derivable from the log alone. |
Inputs
run_id: must be supplied, non-empty, and unique within the log.started_atandended_at: must be supplied as ISO 8601 UTC timestamps (YYYY-MM-DDTHH:mm:ssZ). The entry date guard is derived fromended_at.metrics: must be supplied as a JSON object of run measurements (for example, duration, token count, model, outcome). Aggregates are computed from these fields alone.log_path: must be supplied; path to the append-only JSONL run log.last_run_pointer_path: must be supplied; path to the last-run pointer file.retention_window: optional; an ISO 8601 duration or day count. When omitted, no pruning is performed.
Procedure
- Validate inputs at the trust boundary before any mutation:
run_idis non-empty;started_atandended_atparse as ISO 8601 UTC andended_atis not beforestarted_at;metricsis a JSON object. Reject any timestamp that is not ISO-only. Scan the log for an existing line whose parsedrun_idequals the supplied one; if found, stop withrejected-duplicateand do not mutate. Done when: inputs parse and no duplicaterun_idexists. - Choose the update path. Without
retention_window, openlog_pathin append-only mode. Withretention_window, prepare an atomic compaction using a same-directory temporary file; keeplog_pathunchanged until the replacement is complete, and remove incomplete temporary output on failure. Done when: the applicable path is selected. - Compose one JSONL entry as a single line:
run_id,started_at,ended_at,metrics, anddateset to the ISO date portion ofended_atas the date guard. Done when: the entry is a single line with all fields and metrics sufficient to derive aggregates. - Without
retention_window, append the entry as exactly one newline-terminated line and flush; do not alter any prior line. Withretention_window, add the entry to the staged compacted file instead of appending tolog_path. Done when: exactly one line with thisrun_idwill be present in the final log. - If
retention_windowis supplied, compute the cutoff from the current UTC date minus the window. Drop only parseable lines whosedateprecedes the cutoff; preserve all other existing lines byte-for-byte. Atomically replacelog_pathonly after the replacement is complete; on staging failure, remove the temporary file and leavelog_pathunchanged. Done when: expired lines are absent and surviving lines are unaltered. - Update the last-run pointer at
last_run_pointer_pathto an object containing the newrun_idandended_at. Done when: the pointer contains the newrun_idandended_at.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago Changed 27e9bb5ca650
- 1mo ago Changed · +1 lines b7bae97729ec
- 1mo ago Changed · -29 tokens per session d5d52da8933f
- 1mo ago First seen · 45 lines · 63 tokens per session scan A 601eefc8a138
append-run-log is a skill published in the GitHub repository OutlineDriven/outline-driven-development (53 stars, last pushed 22d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,214 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.