principal-pi-skills 4.7.1 → 4.7.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +10 -10
- package/CHANGELOG.md +32 -0
- package/README.md +18 -66
- package/package.json +1 -2
package/AGENTS.md
CHANGED
|
@@ -132,27 +132,27 @@ assumptions-not-questions rule, the final-message-only rule. Anything outside a
|
|
|
132
132
|
to every output.
|
|
133
133
|
|
|
134
134
|
When maintaining this package, put lasting regressions in existing behavior/domain suites,
|
|
135
|
-
not PR-named files. `npm test` checks current contracts
|
|
136
|
-
|
|
137
|
-
Report those counts separately. Preserve archived evidence and its original candidate identity.
|
|
135
|
+
not PR-named files. `npm test` checks current contracts and product behavior.
|
|
136
|
+
Behavioural measurement—including the fidelity corpus and skill-harness evidence—lives in [principal-pi-skills-evals](https://github.com/mojomanyana/principal-pi-skills-evals); routing checks live here.
|
|
138
137
|
|
|
139
138
|
## Setup (pi)
|
|
140
139
|
|
|
141
|
-
1. `pi install git:github.com/mojomanyana/principal-pi-skills@v4.7.
|
|
140
|
+
1. `pi install git:github.com/mojomanyana/principal-pi-skills@v4.7.3` installs the eight
|
|
142
141
|
skills, the four `/principal-*` commands, and the bootstrap
|
|
143
142
|
extension, which loads automatically with the package. Install a tag, not a branch.
|
|
144
|
-
2. Subagents (optional): before npm publication, latest is 4.
|
|
143
|
+
2. Subagents (optional): before npm publication, latest is 4.7.2 and npm @4.7.3 is not
|
|
145
144
|
yet available. Use the installed tagged package's `scripts/install-agents.mjs` with Node
|
|
146
145
|
(`install`, then `check`), locating its actual path rather than assuming a universal Pi
|
|
147
146
|
install directory. Alternatively follow the concrete verified-tag disposable checkout
|
|
148
147
|
recipe in [README Install](README.md#install-pi). After npm publication, pin both:
|
|
149
|
-
`npx -p principal-pi-skills@4.7.
|
|
150
|
-
`npx -p principal-pi-skills@4.7.
|
|
148
|
+
`npx -p principal-pi-skills@4.7.3 principal-pi-agents install` and
|
|
149
|
+
`npx -p principal-pi-skills@4.7.3 principal-pi-agents check`.
|
|
151
150
|
The five definitions go to `${PI_CODING_AGENT_DIR:-~/.pi/agent}/agents`; foreign files
|
|
152
151
|
are refused. Without them, the routing table still runs inline.
|
|
153
|
-
Version 4.7.
|
|
154
|
-
|
|
155
|
-
separate: before the new tag exists,
|
|
152
|
+
Version 4.7.3 refreshes release and external-measurement documentation without changing
|
|
153
|
+
runtime contracts; behavioral measurement remains in `principal-pi-skills-evals` while routing
|
|
154
|
+
checks remain here. Tag creation and npm publication are separate: before the new tag exists,
|
|
155
|
+
validate the actual candidate's skills and installer
|
|
156
156
|
in isolation. Recorded model/evidence limitations remain; a release tag does not erase them.
|
|
157
157
|
3. Context handoff (pi-daddy 0.33.0+): each skill's `allowed-tools` sets how much of this
|
|
158
158
|
session a delegated child may receive. `architect`, `decide` and `plan` allow
|
package/CHANGELOG.md
CHANGED
|
@@ -6,6 +6,38 @@ Where review revealed a prior claim or design decision didn't hold up under clos
|
|
|
6
6
|
|
|
7
7
|
---
|
|
8
8
|
|
|
9
|
+
## [4.7.3] — 2026-10-06
|
|
10
|
+
|
|
11
|
+
**Changed — current release and measurement documentation.** Installation examples and
|
|
12
|
+
subagent pins now target the immutable `v4.7.3` release; before npm publication, the documented
|
|
13
|
+
registry latest is 4.7.2 and npm `@4.7.3` remains unavailable. Previously the documentation
|
|
14
|
+
still described 4.7.2 as unpublished after it became npm `latest`.
|
|
15
|
+
|
|
16
|
+
**Documented — external frozen-rubric baseline.** The README now links the current
|
|
17
|
+
[principal-pi-skills-evals baseline](https://github.com/mojomanyana/principal-pi-skills-evals/blob/main/BASELINE.md),
|
|
18
|
+
which records DeepSeek V4.1 Flash at 56/158 (35%) with 2 infrastructure-error scenarios
|
|
19
|
+
and Nemotron Lightning at 28/158 (18%) with 12. Infrastructure errors are retained as
|
|
20
|
+
non-passes, both subjects remain NOT READY across all eight skills, and the observations
|
|
21
|
+
include disclosed infrastructure gaps; they do not change or qualify the runtime package.
|
|
22
|
+
|
|
23
|
+
**Compatibility.** No skill, agent, prompt, bootstrap, generated contract, tool ceiling, or
|
|
24
|
+
runtime behavior changed from 4.7.2. Tag creation and npm publication remain separate.
|
|
25
|
+
|
|
26
|
+
## [4.7.2] — 2026-10-01
|
|
27
|
+
|
|
28
|
+
**Changed — behavioral measurement moved out (#59).** The requirement-fidelity corpus,
|
|
29
|
+
skill-harness specifications and results, retained evidence, replay tooling, and their
|
|
30
|
+
repository tests now live in
|
|
31
|
+
[principal-pi-skills-evals](https://github.com/mojomanyana/principal-pi-skills-evals).
|
|
32
|
+
Routing inputs and baselines remain here, and `npm test` now covers only current product and
|
|
33
|
+
contract behavior; previously this repository also retained the behavioral corpus and
|
|
34
|
+
historical evidence checks.
|
|
35
|
+
|
|
36
|
+
**Reaffirmed — the 4.0.1 boundary.** Behavioral measurement belongs in the external
|
|
37
|
+
measurement repository rather than this runtime package. PR #59 applies that original 4.0.1
|
|
38
|
+
decision to the later requirement-fidelity material instead of maintaining a local exception.
|
|
39
|
+
No skill, agent, prompt, bootstrap, or generated contract text changed.
|
|
40
|
+
|
|
9
41
|
## [4.7.1] — 2026-10-01
|
|
10
42
|
|
|
11
43
|
**Combined release candidate — all requirement-fidelity work and repairs (#58).** This
|
package/README.md
CHANGED
|
@@ -125,7 +125,7 @@ bootstrap/BOOTSTRAP.md routing table + Next: vocabulary + model t
|
|
|
125
125
|
extensions/bootstrap.ts pi extension: injects BOOTSTRAP.md at session start and after compaction
|
|
126
126
|
scripts/ generator, installers, and checks behind `npm test`
|
|
127
127
|
tests/{unit,install}/ current product/contract + clean-home install tests (node:test)
|
|
128
|
-
|
|
128
|
+
evals/{triggers.json,adversarial-triggers.json,baseline/} routing checks and baselines
|
|
129
129
|
AGENTS.md routing + dispatch reference; the bootstrap injects its table automatically
|
|
130
130
|
CHANGELOG.md release history
|
|
131
131
|
```
|
|
@@ -135,10 +135,10 @@ CHANGELOG.md release history
|
|
|
135
135
|
1. **Skills + prompts** — install an immutable tag, not a branch:
|
|
136
136
|
|
|
137
137
|
```
|
|
138
|
-
pi install git:github.com/mojomanyana/principal-pi-skills@v4.7.
|
|
138
|
+
pi install git:github.com/mojomanyana/principal-pi-skills@v4.7.3
|
|
139
139
|
```
|
|
140
140
|
|
|
141
|
-
The v4.7.
|
|
141
|
+
The v4.7.3 `pi` manifest registers the eight skills, the four `/principal-*` commands,
|
|
142
142
|
and the bootstrap extension — it loads automatically with
|
|
143
143
|
the package; there is no separate extension-install step. Unpinned `main` moves under
|
|
144
144
|
you, so install a tag if you want a fixed, nameable behavior.
|
|
@@ -148,8 +148,8 @@ CHANGELOG.md release history
|
|
|
148
148
|
and reports success. `2.3.1` is the lowest safe version.
|
|
149
149
|
|
|
150
150
|
2. **Subagents (optional).** Use the **same source** as the installed skills. Before npm
|
|
151
|
-
publication, npm latest is 4.
|
|
152
|
-
and npm `@4.7.
|
|
151
|
+
publication, npm latest is 4.7.2; unpinned `npx` would install/check older definitions,
|
|
152
|
+
and npm `@4.7.3` is not yet available. Either locate the actual installed tagged package
|
|
153
153
|
(its path varies by Pi configuration) and run its `scripts/install-agents.mjs` with Node,
|
|
154
154
|
or use this concrete matching-tag disposable checkout recipe:
|
|
155
155
|
|
|
@@ -158,8 +158,8 @@ CHANGELOG.md release history
|
|
|
158
158
|
set -eu
|
|
159
159
|
source_dir=$(mktemp -d)
|
|
160
160
|
trap 'rm -rf -- "$source_dir"' EXIT
|
|
161
|
-
git clone --depth 1 --branch v4.7.
|
|
162
|
-
test "$(git -C "$source_dir/package" rev-parse HEAD)" = "$(git -C "$source_dir/package" rev-parse 'v4.7.
|
|
161
|
+
git clone --depth 1 --branch v4.7.3 https://github.com/mojomanyana/principal-pi-skills.git "$source_dir/package"
|
|
162
|
+
test "$(git -C "$source_dir/package" rev-parse HEAD)" = "$(git -C "$source_dir/package" rev-parse 'v4.7.3^{commit}')"
|
|
163
163
|
git -C "$source_dir/package" rev-parse HEAD # retain the resolved source identity
|
|
164
164
|
node "$source_dir/package/scripts/install-agents.mjs" install
|
|
165
165
|
node "$source_dir/package/scripts/install-agents.mjs" check
|
|
@@ -169,14 +169,15 @@ CHANGELOG.md release history
|
|
|
169
169
|
After npm publication, and only once the matching package is available, pin both commands:
|
|
170
170
|
|
|
171
171
|
```sh
|
|
172
|
-
npx -p principal-pi-skills@4.7.
|
|
173
|
-
npx -p principal-pi-skills@4.7.
|
|
172
|
+
npx -p principal-pi-skills@4.7.3 principal-pi-agents install
|
|
173
|
+
npx -p principal-pi-skills@4.7.3 principal-pi-agents check
|
|
174
174
|
```
|
|
175
175
|
|
|
176
|
-
Version 4.7.
|
|
177
|
-
|
|
178
|
-
|
|
179
|
-
|
|
176
|
+
Version 4.7.3 refreshes release and measurement documentation without changing skill,
|
|
177
|
+
agent, prompt, or bootstrap behavior. Behavioral measurement remains in the separate
|
|
178
|
+
`principal-pi-skills-evals` repository, while routing checks remain here. Use the commands
|
|
179
|
+
above after the v4.7.3 tag exists; npm publication is separate. The checkout check verifies
|
|
180
|
+
tag/HEAD consistency, not independent tag trust;
|
|
180
181
|
compare the recorded SHA with the release identity when provenance matters. Before tagging,
|
|
181
182
|
validate the actual candidate's skills and installer in an isolated `PI_CODING_AGENT_DIR`.
|
|
182
183
|
Known behavioral qualification limits remain documented; combining the release does not waive them.
|
|
@@ -232,17 +233,9 @@ CHANGELOG.md release history
|
|
|
232
233
|
|
|
233
234
|
`npm test` remains the free gate: generated-contract drift, word budgets, frontmatter lint,
|
|
234
235
|
installer and tarball behavior, `Next:` transition parity, and deterministic source-fidelity
|
|
235
|
-
contract assertions
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
`npm run verify:evidence` separately runs `node --test tests/evidence/*.test.mjs`:
|
|
239
|
-
offline historical receipt/hash integrity, retained failed observations, and fail-closed
|
|
240
|
-
replay-parser checks. It never invokes Pi or a model; the parser check skips with a reason
|
|
241
|
-
if optional Python is absent. It is not part of `npm test` or default CI. Passing it does
|
|
242
|
-
not qualify current model behavior or restamp an archived candidate. Historical test
|
|
243
|
-
totals (including 141 unit tests) describe their recorded runs, not today's suite size.
|
|
244
|
-
Archived manifests retain their original candidate identity even when the working tree
|
|
245
|
-
has changed; reports, raw traces and manifests are not rewritten by test cleanup.
|
|
236
|
+
contract assertions. These check current product contracts, not model behavior or instruction delivery.
|
|
237
|
+
|
|
238
|
+
Behavioural measurement—including the requirement-fidelity corpus and skill-harness evidence—lives in [principal-pi-skills-evals](https://github.com/mojomanyana/principal-pi-skills-evals); routing checks live here. Its [current frozen-rubric baseline](https://github.com/mojomanyana/principal-pi-skills-evals/blob/main/BASELINE.md) reports DeepSeek V4.1 Flash at 56/158 (35%) with 2 infrastructure-error scenarios and Nemotron Lightning at 28/158 (18%) with 12; infrastructure errors are retained as non-passes, and both subjects remain NOT READY across all eight skills. These observations include disclosed infrastructure gaps and do not change this package's runtime contracts.
|
|
246
239
|
|
|
247
240
|
**Enforcement boundary:** Build/Review instructions ask the model to organize regressions
|
|
248
241
|
by lasting behavior, not PR/finding IDs, and distinguish product coverage from historical
|
|
@@ -255,47 +248,6 @@ The package commands and CI mechanically select suites; pi-daddy's delegated too
|
|
|
255
248
|
control available capabilities, not test names or correctness. Refresh installed skill/agent
|
|
256
249
|
definitions when adopting a revision: editing this checkout does not update another installed copy.
|
|
257
250
|
|
|
258
|
-
A narrow local opt-in behavioral regression corpus is authorized for requirement fidelity,
|
|
259
|
-
superseding only the blanket removal of focused harness fixtures below. It is **partially measured, not fully qualified**:
|
|
260
|
-
46 runnable component cases now live in `<skill>/tests/specification.yaml` for Plan, Build,
|
|
261
|
-
Review, Investigate, Decide, Architect and Debug. Shared synthetic fixtures, 51-row long-source
|
|
262
|
-
oracle, all F01–F27 status/replay recipes and runner limitations are documented in
|
|
263
|
-
[evals/requirement-fidelity/README.md](evals/requirement-fidelity/README.md), with an
|
|
264
|
-
[evidence index](evals/requirement-fidelity/evidence.md). The three evidence-scope cases have
|
|
265
|
-
[bounded live observations](evals/requirement-fidelity/evidence/evidence-scope/README.md):
|
|
266
|
-
F25/F27 raw PASS; F26's old reporting failure is retained, with a
|
|
267
|
-
[new corrected-rubric PASS and separate execution audit](evals/requirement-fidelity/evidence/regression-evidence-alignment/README.md).
|
|
268
|
-
[Whole-PR repairs](evals/requirement-fidelity/evidence/full-review-repairs/README.md)
|
|
269
|
-
retain the earlier report-safety observations and 5/9 run.
|
|
270
|
-
[Latest Build handoff validation](evals/requirement-fidelity/evidence/build-handoff/README.md)
|
|
271
|
-
is **4/9 NOT READY**; three fully captured cases verify saved patches and functional regressions
|
|
272
|
-
but retain caveat-delivery, persistence-stop and reproducibility limitations.
|
|
273
|
-
The earlier narrow direct audit remains UNVERIFIED with explicit manual inspection.
|
|
274
|
-
Older 43-case results remain historical.
|
|
275
|
-
Retained live runs include failures;
|
|
276
|
-
a manually orchestrated source→plan→build→review chain, full long-plan inspection, and two
|
|
277
|
-
normal skill-loading probes provide narrower positive evidence, not an all-case pass.
|
|
278
|
-
PR #58 retains three direct blocking runs of the unchanged critical F04 negative and three
|
|
279
|
-
successful supplied-definition companions. Actual registered workflow prompts demonstrate
|
|
280
|
-
repeat-report preservation, absent-ignore initialization and an approval-gated inline bugfix.
|
|
281
|
-
These are bounded observations, not passing harness grades; fresh-session resumed repair and
|
|
282
|
-
delegated transport remain unmeasured. Three parent-only replay recipes track partial coverage.
|
|
283
|
-
Retain results.yaml, synthetic transcripts/traces, changed-file diffs
|
|
284
|
-
and complete output artifacts under `<skill>/tests/results/<runner-model>/<run>/`; use narrow
|
|
285
|
-
ignore rules for incidental caches/HTML only. Review evidence for secrets before staging.
|
|
286
|
-
No model calls in `npm test`, no harness runtime dependency, no fixtures/results in the npm
|
|
287
|
-
package. Broad comparisons and qualification remain external.
|
|
288
|
-
|
|
289
|
-
Record candidate/spec/fixture identities, runner/Pi versions, subject/judge, mode, repetitions,
|
|
290
|
-
commands and retained artifacts. Separate forced instruction following from normal runtime
|
|
291
|
-
loading; missing delivery/retention evidence is UNKNOWN, never PASS. Installed skill-harness
|
|
292
|
-
0.21.0 preflight exposed schema-2 and retention gaps; no compatible published update is
|
|
293
|
-
available per the implementation preflight. P0/schema-3/full behavioral validation has not
|
|
294
|
-
passed. An unsupported Spark provider response prevented lower-cost robustness measurements;
|
|
295
|
-
CLI exit zero was not counted as success. Remaining Build/Architect failures, tool-ceiling
|
|
296
|
-
violations, and unmeasured combinations are recorded rather than waived. No prior deleted
|
|
297
|
-
4/4 claim is restored. Focused results establish only their recorded candidate/model/delivery cells.
|
|
298
|
-
|
|
299
251
|
Two opt-in routing checks use only the eight authored frontmatter descriptions. Run
|
|
300
252
|
`npm run check:routing-collisions` for all 56 directed description pairs and
|
|
301
253
|
`npm run check:routing-triggers` for the three-run synthetic trigger suite. Both require
|
|
@@ -328,7 +280,7 @@ Decisions taken for 4.0, all closed:
|
|
|
328
280
|
| Build delegation | `principal-build` agent; inline when there is no multi-step plan file or no subagent tool |
|
|
329
281
|
| Plan persistence | multi-step plans to git-ignored `.principal/plans/<slug>.md`; no date prefix because plan has no clock, and resume matches on the `## Plan:` line |
|
|
330
282
|
| Decide vs architect | both kept; decide answers "should we / which", architect answers "how is it structured" |
|
|
331
|
-
| Measurement |
|
|
283
|
+
| Measurement | behavioural measurement lives in [principal-pi-skills-evals](https://github.com/mojomanyana/principal-pi-skills-evals); routing checks stay here |
|
|
332
284
|
|
|
333
285
|
Two implementation notes that differ from the obvious reading: the bootstrap is injected as
|
|
334
286
|
a user-role message wrapped in `<IMPORTANT>`, because pi's `context` hook can only insert
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "principal-pi-skills",
|
|
3
|
-
"version": "4.7.
|
|
3
|
+
"version": "4.7.3",
|
|
4
4
|
"description": "Skill framework for principal-level software engineering: eight skills (decide, architect, plan, build, review, debug, investigate, git-ops), a pi bootstrap, and two approval-gated workflows.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"author": "Nemanja Alavanja",
|
|
@@ -22,7 +22,6 @@
|
|
|
22
22
|
},
|
|
23
23
|
"scripts": {
|
|
24
24
|
"test": "npm run generate:check && npm run test:unit && npm run test:install && npm run check:pack && npm run lint:skills",
|
|
25
|
-
"verify:evidence": "node --test tests/evidence/*.test.mjs",
|
|
26
25
|
"test:unit": "node --test tests/unit/*.test.mjs && node scripts/check-word-budgets.mjs",
|
|
27
26
|
"generate": "node scripts/generate-contracts.mjs",
|
|
28
27
|
"generate:check": "node scripts/generate-contracts.mjs --check",
|